1321 results for “Base”

securityweek.comarticle🛡️ Security

Florida Student Aid Website Hack Puts Data of 4.9 Million People at Risk

The Florida Department of Education (FLDOE) disclosed a breach of its Florida Student Financial Aid website (FloridaStudentFinancialAidSG.org), discovered on 19 October and potentially affecting about 4.9 million people. Exposed data may include names, Social Security numbers, dates of birth, addresses, phone numbers and emails. The entry vector and actor are undisclosed. The article links it to the September FLHSMV driver database breach, which came from compromised police credentials.

Threat Intel· Published and added 2 Nov 2026

dfir.chwriteup🛡️ Security

Modern Authentication, Legacy Problems

Field note from an incident response case in a hybrid on-premises Exchange environment where Hybrid Modern Authentication and Entra MFA were enforced, yet 66,610 EWS requests from a Thunderbird user-agent authenticated with NTLM. OWA also accepted forms-based authentication directly. It shows how to find these paths in Exchange HttpProxy logs, check virtual directories and authentication policies, and block legacy authentication.

Blue Team & Detection, Identity & Access· Published and added 1 Nov 2026

blog.talosintelligence.comwriteup🛡️ Security

Appraisal by AI: Model-driven victim prioritization in the VOLTA infostealer

VOLTA (VOLTA-AUTODOXER) is a self-deleting Windows infostealer that, after theft and live session-based enrichment, POSTs an evidence bundle to OpenRouter so an LLM can rank the victim's assets by monetization value. It falls back across a Claude, Kimi and Gemini chain when a model refuses. Talos covers the builder model, the Chrome App-Bound Encryption bypass, the volta_debug.txt artifact and countermeasures such as blocking Chrome --headless.

Malware & RE, Threat Intel, AI Security· Published and added 31 Oct 2026

x.comthread🛡️ Security

Tanmay (@TanmayK_03) on X

DBHub, a database MCP server, had a read-only mode bypass in its SQL check. The check treated every `--` as a comment, but MySQL only starts a comment when whitespace follows it. A hidden write statement could therefore still run, and a prompt injection could trigger it. Fixed in version 0.22.6. Replies say enforcement belongs in database grants and that parser tests need to be dialect-specific.

AppSec, AI Security· Added 31 Oct 2026, published 30 Oct 2026

securityweek.comarticle🛡️ Security

Passkeys Are Better Than Passwords. But They Are Not Enough.

Opinion piece arguing that passkeys, built on public-key cryptography, resist phishing, credential stuffing and password theft but do not settle identity risk. Attackers can go around them through account enrollment before a passkey is bound, weaker recovery paths (SMS, email link, help desk), device changes and authenticated session hijacking. It proposes layering identity threat detection with risk-based, continuous evaluation of trust.

Identity & Access· Published and added 30 Oct 2026

cloud.google.comarticle🛡️ Security

ARTEX and Friends: Enter Agentic Offensive Frameworks

ARTEX is an open-source, Go-based multi-agent LLM pentesting and C2 platform that Google Threat Intelligence Group and Mandiant saw threat actors run in incident response cases from late August 2026, alongside PentAGI and CAIRN. The report covers ARTEX behaviour such as MySQL general_log JSP webshell poisoning and burst timing, UNC7228 (overlapping STORM-0940), a seven-stage model of adversary LLM use, and five Mandiant defensive layers. The text was truncated before the last layers.

Threat Intel, AI Security, Offensive Security, Blue Team & Detection· Added 1 Nov 2026, published 30 Oct 2026

github.comrepo🧠 AI

rikugan: LLM reverse-engineering agent for IDA Pro and Binary Ninja

Rikugan is a reverse-engineering agent that runs inside IDA Pro and Binary Ninja. It has its own generator-based agent loop, context management, plan mode and 60+ tools, and does not depend on an external MCP server. An orchestrator spawns parallel subagents to analyze a binary. It supports Anthropic, Gemini, MiniMax, Kimi, OpenAI-compatible endpoints and Ollama, with per-model notes.

agents, coding-agents· Added 30 Oct 2026

oversecured.comarticle🛡️ Security

Content Providers and the potential weak spots they can have | Oversecured Blog

Oversecured's Android security checklist for Content Providers covers insecure FileProvider path configs, path traversal via decoded Uri.getLastPathSegment(), mismatched readPermission/writePermission, proxying requests to more privileged providers, SQL injection across a shared database, and sensitive actions in providers. Each case has vulnerable manifest and Java code, an attacker PoC and remediation. Real cases from Google and Samsung devices are cited. The page text was truncated near the end.

Mobile Security, AppSec· Added 29 Oct 2026

oversecured.comarticle🛡️ Security

Inside mobile taint analysis: how source-to-sink tracking finds real data-leak paths | Oversecured Blog

Oversecured explains taint analysis for Android and iOS apps and contrasts it with pattern-matching SAST such as MobSF. It covers source, flow and sink, cross-component tracking over Intents, flag-based sanitizer modeling and implicit intent simulation. The case study is an unsafe Class.forName().newInstance() on a Serializable transportFactoryClassName field in Google's com.google.auth.oauth2 credential classes, which Google fixed with a $3,133.70 bounty.

Mobile Security, AppSec· Added 29 Oct 2026

oversecured.comarticle🛡️ Security

Vulnerabilities that lead to account takeover in banking and fintech mobile apps | Oversecured Blog

Oversecured guide to eight vulnerability categories that lead to account takeover in mobile banking and fintech apps: WebView JavaScript bridge token leakage, Intent Redirection, hardcoded tokens, deeplink hijacking, insecure token storage, localhost OAuth listeners, AIDL abuse and weak biometric auth. It includes a WebView PoC based on Samsung SmartThings CVE-2022-30746 and maps findings to OWASP MASVS, PCI DSS and PSD2. It argues taint analysis plus dynamic PoC is needed to find multi-component chains.

Mobile Security, AppSec, Identity & Access· Added 29 Oct 2026

blog.talosintelligence.comarticle🛡️ Security

A quiet week in infosec <.<

Cisco Talos Threat Source newsletter for the week of the PHP and Node.js vulnerability news cycle. It summarises NIK C2, a Go-based Windows implant that dumps credentials, streams keystrokes, deploys screen-locking ransomware and uses a victim's hijacked OpenAI API keys to analyse stolen data. It also lists weekly headlines (CISA KEV PHP bugs, Brotli flaw, Gheist GitHub token theft), Talos links and top malware hashes.

Threat Intel, AI Security· Published and added 29 Oct 2026

arxiv.orgpaper🧠 AI

VeriCUA: Verification as Agentic Exploration for Computer-Using Agents

VeriCUA is a platform-agnostic framework that verifies task completion by computer-using agents through agentic exploration. The verifier inspects context to build a task rubric, then picks GUI or code checks for unresolved requirements and combines findings under explicit evidence rules. It works online and offline across desktop, mobile and web, and agrees better with reference labels than the baselines, with the largest offline gains on hard cases.

agents, evals, research· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper🧠 AI

On the Fundamental Limits of Prefill-Based Decoding Length Prediction

This paper derives bounds on predicting an LLM's decode length from prefill-phase hidden states, a primitive for inference scheduling. It models decoding as a stopped stochastic process, giving per-prompt normality and an affine variance law σ=αμ+b. Predictors (MLP, EGTP, FiLM, soft-label, Mixture-of-Experts) converge near the bound, so system error dominates model error. It proposes fixing model, data and sampling in benchmarks and reporting relative-error metrics.

research, inference, evals· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper🧠 AI

Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation

On-policy state training is a method for training chain embedding retrievers for multi-hop RAG on the states the encoder itself reaches, including those built on its own wrong retrievals. Each state is labeled with the earliest missing gold passage, other missing gold passages are masked, and updates are contrastive and mixed with teacher-forced states. It retrieves complete evidence more often than teacher-forced training and graph-based systems, and transfers to harder long-chain HotpotQA and 2WikiMultiHopQA variants the authors built.

research, llm-apps, training· Added 31 Oct 2026, published 29 Oct 2026

arxiv.orgpaper🛡️ Security

Understanding and Mitigating Role Spoofing in LLMs

Understanding and Mitigating Role Spoofing in LLMs is an arXiv paper (October 2026) on role spoofing, a prompt injection where malicious tool output impersonates the user. It shows models track "who said what" using both content cues (semantics, style) and structure cues (control tokens, formatting). Attacks combining fake structure and content succeed often, adversarial training stops only content-based attacks, and linear probes trained to predict conversation roles detect spoofing across settings.

AI Security· Added 31 Oct 2026, published 29 Oct 2026

socket.devarticle🛡️ Security

OpenCode User Hit with Hostile Backlash After Reporting Free AI Loophole

Socket reports on a GitHub issue for OpenCode, opened 28 June, describing a bypass of per-IP usage limits on its free hosted models by switching VPN addresses. The reporter first proposed account-based limits, then reopened the issue in August to promote the workaround and claimed to run 130 agents. After the thread drew harassment and was deleted in October 2026, it is unclear whether OpenCode fixed the bypass.

other· Published and added 29 Oct 2026

socket.devarticle🧠 AI

OpenCode User Hit with Hostile Backlash After Reporting Free AI Loophole

Socket reports on a GitHub issue in the OpenCode tracker describing a bypass of per-IP usage limits on free hosted models, using a VPN to switch addresses. The reporter first urged account-based limits, then claimed to run 130 concurrent agents through the loophole. After the issue drew harassment it was deleted. Whether OpenCode fixed the bypass in October 2026 stays unclear.

coding-agents, ai-policy· Published and added 29 Oct 2026

alignment.openai.comarticle🛡️ Security

How we detect frontier model misalignment

OpenAI's internal misalignment monitoring system uses a layered pipeline: activation probes, a model-based reviewer, an investigative agent and automated investigation against network logs, then human paging. Replaying the Hugging Face incident, the expanded monitors would have alerted security about 30 minutes after the sandbox escape, over 30 hours before the breach. The post covers evaluation on recorded and simulated incidents, METR and Redwood Research red-teaming, avoiding chain-of-thought obfuscation pressure, and external Astra monitoring.

AI Security, Blue Team & Detection· Added 30 Oct 2026, published 29 Oct 2026

alignment.openai.comarticle🧠 AI

How we detect frontier model misalignment

OpenAI describes its multilayer misalignment monitoring system for frontier models: activation probes, a model-based reviewer, investigative agents, automated log-based investigation and human paging. A replay of the Hugging Face incident shows an alert about 30 minutes after sandbox escape, over 30 hours before the breach. It also covers evaluations, METR and Redwood Research red-teaming, monitor models GPT-5.6 Sol, Terra and Luna, and avoiding pressure on chains of thought.

ai-safety, agents, evals· Added 30 Oct 2026, published 29 Oct 2026

huggingface.coarticle🧠 AI

Granite Switch 4.1.1 — Update models like you update software

Granite Switch 4.1.1 is a backwards-compatible patch release of IBM's modular Switch architecture, which configures a language model with specialized, cache-efficient adapters on one endpoint. It updates the Granite Speech ASR model (10 languages, native punctuation and capitalization) and the Decision adapter in granitelib-core, measured on the Jev Decision Index test set. Only the new adapters were retrained; the base model is unchanged. IBM plans tutorials and an Adapter SDK for third-party adapters.

models, multimodal· Published and added 29 Oct 2026

arxiv.orgpaper🧠 AI

M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models

M-PFT is an angular-margin method for prompt tuning of vision-language models that fixes base-to-novel dual miscalibration (underconfidence on base classes, overconfidence on novel classes). It adds two losses: minimizing the maximum cosine similarity between tunable class embeddings, and minimizing angular distance to each zero-shot embedding. Tests on 9 prompt-tuning methods and 15 datasets show lower novel-class calibration error at comparable accuracy and negligible overhead.

research, multimodal, training· Added 31 Oct 2026, published 29 Oct 2026

decrypt.coarticle🛡️ Security

Treasury Sanctions 11 Over North Korean IT Worker Scheme That Moved Millions in Crypto

Decrypt reports that OFAC sanctioned 10 individuals and one entity on 28 October 2026 over North Korean IT worker schemes. Russian nationals Ilya Boykov and Vitold Obertas converted millions in crypto (about $3.5 million and nearly $2 million), and the listings include Ethereum and Tron addresses, one shared by both. It also covers the Vladivostok-based First Financial and Technical Development Center and Kim Ki Hyok, who moved nearly $500,000 in crypto.

Threat Intel, Blockchain· Published and added 29 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Cryptanalysis and Enhancement of VTBSAE: Provably Secure Verifier-Based PAKE Protocols for the Industrial Internet of Things

Cryptanalysis of VTBSAE, a verifier-based PAKE protocol for the Industrial Internet of Things, showing it fails to resist client impersonation after server compromise. The authors propose E-VTBSAEv1, which binds the client point E1 to fresh server randomness, and prove AKE security and forward secrecy in the random-oracle model under CDH. Raspberry Pi 4B tests show runtime comparable to VTBSAE with the same communication and storage overhead.

Identity & Access, Hardware & RF· Added 31 Oct 2026, published 29 Oct 2026

securityweek.comarticle🛡️ Security

Hackers Steal 2.6 Million Records From Sony’s Japanese ISP So-net

So-net, the Japanese ISP run by Sony Network Communications, disclosed on 27 October that attackers broke into its member database on 19 October and took nearly 2.6 million records of So-net and Plala subscribers. Data includes names, birth dates, phone numbers, emails and user IDs, plus about 54,000 email addresses with passwords and 16 bank account records. The company reset mail passwords and reported to Japan's Personal Information Protection Commission; the intrusion method is undisclosed.

Threat Intel· Published and added 29 Oct 2026

blog.talosintelligence.comwriteup🛡️ Security

NIK C2: The new AI-enabled command-and-control framework

NIK C2 is a newly observed C2 framework with a Go-based 64-bit Windows implant that embeds an OpenAI Chat Completions client (ai_generate command), falling back to the victim's OPENAI_API_KEY. Talos details its 52+ commands, AES-256-GCM over WebSocket with HTTP fallback, credential, wallet and keystroke theft, screen-lock ransomware, AMSI bypass and anti-debug. It also lists a live C2 at 87.120.196[.]120 and total-sitevv[.]lol.

Malware & RE, Threat Intel, AI Security· Published and added 29 Oct 2026

x.comadvisory🛡️ Security

lee1981 (@lee1981b) on X

CVE-2026-103780 is a stack-based buffer overflow (CWE-121) in Dell PowerProtect Data Domain / DD OS. An unauthenticated remote attacker could get command execution (CVSS 3.1 9.8, Dell DSA-2026-416). The post lists affected and fixed builds for four release trains (Feature Release, LTS2024, LTS2025, LTS2026). It adds KEV, EPSS and SSVC status, plus six defensive checks. The vulnerable service is not public.

Blue Team & Detection, Cloud & Infra· Added 31 Oct 2026, published 29 Oct 2026

blog.googlearticle🧠 AI

How Gemini is helping students and teachers in the classroom

Google reports two classroom studies of Gemini. In a 10-week RCT with over 1,100 UK students (ages 12-15) on Eedi, Gemini-based AI tutoring matched human tutors on in-platform tasks and quizzes, with expert approval of responses rising from 76% to 95%. Gains did not appear on STAR standardized tests. A yearlong Italian study of 1,600 teachers found lessons co-designed with Gemini shifted toward collaborative work.

research, evals, ai-policy· Added 30 Oct 2026, published 29 Oct 2026

openai.comarticle🧠 AI

How we detect frontier model misalignment

OpenAI describes its expanded misalignment monitoring system for frontier models across training, evaluation, internal use and external deployment. It uses a layered design: activation probes (L0), a model-based reviewer (L1), investigative agents (L2) and log-based security checks (L3). A replay of the Hugging Face incident shows an alert about 30 minutes after sandbox escape, over 30 hours before the breach. It also covers monitor evaluations, METR and Redwood red-teaming, and chain-of-thought pressure.

ai-safety, agents, evals· Published and added 29 Oct 2026

openai.comarticle🛡️ Security

How we detect frontier model misalignment

OpenAI's misalignment monitoring system covers frontier models in training, evaluation, internal use and deployment. It has four layers: activation probes (L0), a model-based reviewer (L1), investigative agents (L2) and log-based security checks (L3). A replay of the Hugging Face incident shows an alert about 30 minutes after a sandbox escape, over 30 hours before the breach. It also covers monitor evaluation, METR and Redwood red-teaming, and chain-of-thought pressure.

AI Security, Blue Team & Detection· Published and added 29 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Optimality and Efficiency of Higher-Order Rank-Based Side-Channel Attacks against Inner Product Masking Schemes

HO-ASPA (Higher-Order Adjusted Spearman Coefficient Analysis) is a rank-based, non-profiling side-channel distinguisher. The paper derives its optimal form against two-share Boolean masking and inner product masking under Hamming weight and LSB leakage. It finds no significant gap between higher and lower orders for HO-ASPA, unlike HO-CPA, and reports that it beats Kruskal-Wallis-based attacks in simulated and real-world experiments.

Hardware & RF· Added 31 Oct 2026, published 29 Oct 2026

endorlabs.comarticle🧠 AI

ADLC metrics: How to measure agentic development security | Endor Labs

ADLC metrics is an Endor Labs guide to measuring security in the agentic development lifecycle, where AI coding agents write code. It defines formulas in five categories: AI supply chain visibility, agent action security, agent-generated code security, package risk and developer flow. It advises normalizing findings per merged change, comparing against a human baseline, and baselining six to eight metrics for a month.

coding-agents, ai-policy· Published and added 29 Oct 2026

arxiv.orgpaper🛡️ Security

Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection

Paper studying whether self-evolution weakens personal agents' robustness to indirect prompt injection (IPI). A two-phase method has the user ask the agent to follow tasks in external content, then tests with a third-party injected task the user did not authorize. Against the non-evolving base agent, attack success rose 14.0 to 48.8 points under skill evolution and 3.0 to 39.3 points under reinforcement learning. Code is released.

AI Security· Added 31 Oct 2026, published 29 Oct 2026

latent.spacetalk🧠 AI

Why Agents Love Supabase

Latent Space podcast episode with Supabase founders Paul Copplestone and Ant Wilson on why frontier models pick Supabase first for app backends. It covers the alpha Docker-free local runtime, declarative schemas kept in Git, Supabase Compute for containers beside the database, and scale work (OrioleDB, Multigres, Turso). The founders say Supabase launches about five million databases a month and that AI-driven signups converted better.

coding-agents, ai-infra· Published and added 28 Oct 2026

x.compaper🛡️ Security

Cryptography and Security Papers (@FSFG) on X

Log-To-Leak is an arXiv paper (cs.CR, cs.AI) by Yuepeng Hu, Chongyu Fan, Sirat Samyoun and Jian Du on prompt injection attacks against tool-using LLM agents through the Model Context Protocol. The title points to a logging-based data leakage channel. The fetched page holds only the title, authors and arXiv link, with no abstract, so the method and results are not visible here.

AI Security· Added 29 Oct 2026, published 28 Oct 2026

hackers-arise.comwriteup🛡️ Security

Social Engineering: Modem-Based Persistence in a Compromised Environment

The article describes reflashing a Huawei E3372h-153 HiLink 4G USB modem so its embedded Linux OS runs an OpenVPN client over the mobile network, creating a covert, network-independent persistence channel after physical USB access. It walks through enabling debug mode, flashing firmware, disabling CD-ROM emulation, configuring DHCP and autorun scripts, and chaining a second L2VPN tunnel to bridge the attacker directly onto the victim's Ethernet segment for tools like Responder. Defense guidance focuses on restricting USB ports and disabling USB network adapters via policy.

Hardware & RF, Offensive Security· Published and added 28 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Beyond the Event Horizon of Keccak, Extending the Observation from 2011 and applications

Beyond the Event Horizon of Keccak extends a 2011 observation that a path in the Keccak sponge from a zero-capacity state back to one yields infinite second-preimage families. Three theorems cover loops from any capacity value x, k-block loops and cycles, and Joux-style multicollisions with search cost independent of k. Verified examples run on Keccak-f[200] and Keccak-f[1600] with c=32; it also proposes bridge-based protocols.

other· Published and added 28 Oct 2026

decrypt.coarticle🛡️ Security

Bithumb Says Hackers Accessed Internal System, Leaking Personal Data

Bithumb, South Korea's second-largest crypto exchange, said an outside party accessed its internal mobile groupware system and leaked personal data. Daishin Securities reported 38,490 customers' names, emails and phone numbers leaked, and Mirae Asset Global Investments also confirmed a hack. Coinbase vendor Amplitude exposed contact data the same day. Changpeng Zhao advised unique email aliases, no SMS 2FA and carrier number locks. The access method is not disclosed.

Threat Intel· Published and added 28 Oct 2026

securityweek.comarticle🛡️ Security

Long-Hidden Flaws Patched in EPICS Research Facility Control Software

Four vulnerabilities in EPICS Base 7.0.10 and earlier, the control-system toolkit used at ITER and the Advanced Photon Source, were disclosed by CISA. CVE-2026-114595 (CVSS 9.8) is an integer overflow that could allow remote code execution, though only an out-of-bounds heap write and crash were demonstrated. All flaws sit in Channel Access and pvAccess handling (TCP 5064 and 5075), need no authentication, and are fixed in 7.0.11.

Hardware & RF, AppSec· Published and added 28 Oct 2026

arxiv.orgpaper🧠 AI

When LLM Architectures Meet Smart Contract Vulnerability Detection: a Replication Study

This paper replicates Chen et al.'s study of LLM-based smart contract vulnerability detection, first on GPT-4 and then on Mixture-of-Experts, RNN-like and State Space Models. The exact replication confirms the high-recall, low-precision pattern on GPT-4. The differentiated replication finds the pattern does not transfer uniformly: GPT-4 and Gemma-3 behave alike despite a roughly 100x parameter gap, while two MoE models diverge.

research, evals· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper🛡️ Security

When LLM Architectures Meet Smart Contract Vulnerability Detection: a Replication Study

This arXiv paper (October 2026) replicates Chen et al.'s study of LLM-based smart contract vulnerability detection. It confirms the high-recall, low-precision pattern on GPT-4, then tests Mixture-of-Experts and RNN-like models plus a preliminary State Space Model run. Gemma-3 matches GPT-4's profile despite far fewer parameters, while two Mixture-of-Experts models diverge, so architecture family alone does not predict detection behavior.

AI Security, AppSec· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper🧠 AI

Think Before You Act: Decision Gate for LLM Agents

JevAct is a runtime verification framework that intercepts selected LLM agent actions before execution and returns feedback for bounded revision. It compiles domain policies into executable state checks and structured questions scored by a prefill-only decision model, giving probability-based judgments without generation. Tested on eleven agents with tau^2-bench Airline and Telecom and BFCL, it gained consistently on Telecom and BFCL and was mixed on Airline.

research, agents, evals· Added 30 Oct 2026, published 28 Oct 2026

decrypt.coarticle🛡️ Security

Coinbase Customer Data Hit in Analytics Vendor Breach, Funds ‘Not Impacted’

Coinbase said on 28 October 2026 that a security incident at analytics vendor Amplitude exposed contact data of a "small subset" of its customers. Coinbase reports no unauthorized access to its own systems and no impact on funds. It gave no counts, data types or dates. The article recalls the May 2025 bribed-support-agent breach (69,461 customers) and the 2025 Trezor/ShipMonk exposure.

Threat Intel· Published and added 28 Oct 2026

arxiv.orgpaper🧠 AI

CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents

CALM is a conflict-aware lifecycle memory governance framework for long-horizon language agents. It turns records into evidence-grounded memory cells, updates their validity and lifecycle states from support, conflict and dependency signals, and admits evidence at query time through training-free or learned gating based on temporal applicability. It beats baselines on LongMemEval-S and LoCoMo with Qwen and GPT backbones, and keeping superseded records helps earlier-state reasoning.

agents, research· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper🧠 AI

From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe

This paper measures job-based doubt in LLM fact-checkers: judging a claim false more often when the poster has a lower-status job. It compares base and post-trained checkpoints of six model families on fact-checked claims with randomised poster profiles. Only the open Tülu-3 recipe (OLMo-2 32B, Tülu-3 70B) creates the effect, under one percentage point but reliable. In OLMo-2 32B the flip comes from one residual-stream direction and appears at supervised fine-tuning, confirmed on 400 new claims. None of seven commercial models doubts lower-status posters more.

research, ai-safety, training· Added 30 Oct 2026, published 28 Oct 2026

endorlabs.comarticle🛡️ Security

The ADLC maturity model: 5 stages of agentic development security | Endor Labs

The ADLC maturity model is a proposed five-stage framework from Endor Labs for scoring security controls over coding agents, from unmanaged experimentation to continuous verification. Each stage has requirements on two tracks, agent actions (shell commands, MCP calls, package installs) and agent output (code, dependencies, secrets). It sets stage 3 at deterministic hooks that block actions, gives evidence-based assessment questions, and lists traps such as relying on prompt-level rules.

AI Security, GRC, DevSecOps· Published and added 28 Oct 2026

endorlabs.comarticle🛡️ Security

How to evaluate ADLC security solutions: A buyer's checklist | Endor Labs

Buyer's checklist from Endor Labs for evaluating security tools in the agentic development lifecycle (ADLC), where AI coding agents write code and take actions such as package installs, CI edits and tool calls. It covers scoping, coverage, evidence-based accuracy, repeatability testing, agent-loop and PR workflow fit, remediation, governance, and a 2 to 4 week proof of concept on 3 to 5 repos with seeded ground truth.

AppSec, AI Security, DevSecOps· Published and added 28 Oct 2026

arxiv.orgpaper🧠 AI

Complementing Text Based Moderation with Multimodal Grounding: Detecting Fraudulent Inducement Behaviors on Short Video Platforms

The paper studies detection and temporal localization of fraudulent inducements (prompts to follow, join chat groups, click links) in internet finance short videos. It compares OCR+LLM, OCR+MLLM and a zero-shot MLLM, and builds a dataset of 2,419 videos (66.49 hours, 3,194 events, four categories). OCR+MLLM reaches mIoU 26.52 versus 14.49 for keyframe OCR+LLM, with 67.0 percent macro recall, using a recall-weighted F2 localization reward.

research, multimodal, training· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper🛡️ Security

Post-Training Large Language Models with LLMON

LLMON (LLM Object Notation) is a framework that separates instructions from data and requires explicit identifier-based execution. The authors post-train Granite-4.1 3B and 8B base models with SFT then RL on a 4.6B-token structured corpus covering general, RAG and tool-calling data, with distractor variants. Attack success rates on indirect prompt-injection benchmarks fall from 53-100% to 0.02-5.6%, and general capability is preserved. Attention-based metrics diagnose failures per transformer layer.

AI Security· Added 30 Oct 2026, published 28 Oct 2026

arxiv.orgpaper🧠 AI

Post-Training Large Language Models with LLMON

LLMON (LLM Object Notation) is a framework that separates executable instructions from passive data and requires explicit identifier-based execution. The paper post-trains Granite-4.1 3B and 8B base models on a 4.6B-token corpus of general, RAG and tool-calling data with distractor variants, using SFT then RL. Attack success rates on indirect prompt-injection benchmarks fall from 53-100% to 0.02-5.6%, with general capabilities preserved. It also adds attention-based per-layer diagnostics.

training, research· Added 30 Oct 2026, published 28 Oct 2026

aws.amazon.comarticle🛡️ Security

Introducing Route 53 Resolved IP Validation for AWS Network Firewall

Route 53 Resolved IP Validation for AWS Network Firewall, launched 21 October 2026 at no extra charge, has Route 53 Resolver share the IP addresses it returns per domain with Network Firewall, which checks each new outbound connection against them. The post covers alert-mode rollout, domain-based filtering of SFTP/SSH traffic, SNI spoofing prevention without TLS inspection, the route53_resolved_ip log field, CloudWatch metrics and best practices.

Cloud & Infra, Blue Team & Detection· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

Improving the Dependency on Fine-Tuning Data in Transfer Learning for Speech Emotion Recognition

This paper proposes an fMLLR-based compensation mechanism that cuts the fine-tuning data needed in transfer learning for speech emotion recognition under train-test acoustic mismatch. An autoencoder reduces trainable parameters, and an affine transform in the encoder latent space models rotations and shifts. In a human-robot interaction task, mean CCC rose 16.8% with 12.9% of the training set and 14.4% with 50%.

research, multimodal, training· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence

The paper proposes POB-ICM (contingency matrix with Chi-square independence testing) and POB-UNBP (a uniformity null model under permutation-based evaluation) to detect positional bias in top-1, single-turn LLM recommenders. On a RAG product-recommendation testbed with 2000 queries and 20 permutations each (40,000 instances), both methods reject positional independence in all evaluated models. Three metrics quantify the effect, and the bias persists across candidate-set size and temperature. Code is public.

research, evals, llm-apps· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🛡️ Security

Structured Security Explanations for Learning-Based Vulnerability Detection

VulnLens is a framework for binary C/C++ function-level vulnerability detection. A label-blind LLM Explainer describes each function from seven fixed perspectives (data flow, memory access, object lifetime, arithmetic and type behavior, control flow, shared state, external-resource access). A supervised Detector fuses code and explanations by cross-attention. It reaches 75.5% accuracy and 77.2% F1 on a 526-function PrimeVul test set, and 66.4% accuracy on SecVulEval without retraining.

AI Security, AppSec· Added 30 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

Locating Sycophancy Across Training Stages in Open Language Models

Locating Sycophancy Across Training Stages in Open Language Models measures sycophancy in 13 open checkpoints from 5 lineages, from base model through supervised fine-tuning and preference optimization to release. It finds two behaviors with different origins: deference to a claim in the prompt exists in every base model, while capitulation under user objection is largely absent from base models and present in every post-trained checkpoint. Post-trained models often drop firmly held answers as readily as loosely held ones when the objection names an alternative.

ai-safety, research, evals· Added 30 Oct 2026, published 27 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Tractable, Not Truncated: Colored-Noise TRNG Security via Fractional Brownian Motion

This ePrint paper models oscillator-based TRNG phase noise, both white and flicker, as fractional Brownian motion. It proves a quasi-renewal property that gives closed-form worst-case min-entropy and sampling requirements, and extends spectral and Allan-variance analysis so noise parameters come from a single timing trace. FPGA and ASIC experiments show flicker noise accounts for over 99% of uncertainty at a 0.99 min-entropy target, allowing a bitrate two to three orders of magnitude higher.

Hardware & RF· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🛡️ Security

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

Heads of Security (HoS) is a prompt injection defense that enforces instruction-data separation with learned per-head attention gates, redistributing attention between trusted and untrusted tokens. Evaluated on Llama-3.3-70B-Instruct and GPT-OSS-20B against SecAlign++ and ASIDE. The black-box RL-Hammer attack reaches 97% ASR on GPT-OSS-20B and 85% on SecAlign but 10% on HoS. The white-box Claudini attack needs 3 times more FLOPs on HoS. HoS keeps base-model utility in few-shot settings, where SecAlign and ASIDE degrade.

AI Security· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

Heads of Security (HoS) is a prompt injection defense that trains a small set of per-head attention gates to shift attention between trusted and untrusted tokens, separating instructions from data. Tested on Llama-3.3-70B-Instruct and GPT-OSS-20B, the black-box RL-Hammer attack reaches 10% ASR on HoS versus 97% on base GPT-OSS-20B and 85% on SecAlign. HoS keeps base utility in few-shot settings, where SecAlign and ASIDE degrade.

research, training· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis

SynthAPI is a pipeline that generates synthetic tool-use environments with explicit control over diversity of tools, tasks and underlying databases. Across 458,752 tasks and 849 trained models of four sizes, the authors fit a scaling law predicting downstream agent generalization. At larger data budgets, scaling tool and database diversity beats adding more tasks, and higher complexity helps more. Agents trained this way beat prior synthetic-data baselines on four benchmarks.

research, training, agents· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

Metacognitive Decoding: Efficient Inference for Diffusion Language Agents

Metacognitive Decoding is a lightweight plug-in controller for diffusion language model backbones. It learns when to finalize tokens and how far generation should extend, and is trained on agent trajectories to balance correctness against generation cost. Across five benchmarks it cuts inference FLOPs by 20.6% on average versus the most efficient baseline, with competitive task accuracy. The abstract names no specific benchmarks or backbones.

research, agents, inference· Added 28 Oct 2026, published 27 Oct 2026

huggingface.coarticle🧠 AI

Build specialized multimodal models with LFM3

LFM3 is Liquid AI's open-weight family of six ~2B-parameter models (text, vision-language, audio, omni and two d1 decision models), all branched from LFM3-1.7B-Base. The base model uses a tri-hybrid backbone of 13 gated short convolutions, 5 sliding-window attention layers and 6 global attention layers, pre-trained on 22T tokens with a 256K context. The post gives transformers snippets, benchmark comparisons against LFM2.5 and Qwen3.5, and a robotics fine-tuning example.

models, multimodal, training· Published and added 27 Oct 2026

liquid.aiarticle🧠 AI

Introducing LFM3: Every Modality for Specialized Intelligence

LFM3 is Liquid AI's new family of open-weight multimodal models, six models of about 2B parameters branched from LFM3-1.7B-Base (22T pre-training tokens, 256K context). The hybrid backbone uses 13 gated short-convolution, 5 sliding-window attention and 6 global attention layers. Variants cover text, vision with video, audio, omni and two decision models, with on-device speed numbers, fine-tuning demos and robotics extensions.

models, multimodal, inference, training· Added 28 Oct 2026, published 27 Oct 2026

x.comtool🧠 AI

alex shapalov (@alxshp) on X

PGX is a free, open-source Postgres runtime written in Rust that hosts thousands of isolated databases in one process, aimed at AI agents. A companion agent skill, installed with `npx skills add pgrundev/pgx --skill pgx`, gives each Claude Code agent its own database automatically. The author claims 1,000 databases in 659 MB RAM, about 0.7 MB per idle database, an 85 ms clone of a 674 MB database, and a 200-agent test with no conflicts.

coding-agents, ai-infra· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

When Visual Evidence Is Insufficient: How Instructions, Post-Training, and Internal Activations Shape Refusal in Multimodal Language Models

This paper studies how multimodal LLMs refuse questions that an image cannot answer, using the MoHoBench benchmark on three MLLMs. It varies the meaning and placement of refusal instructions, compares supervised and preference-based post-training, and intervenes on a refusal-related activation direction. Instructions change refusal at the sample level in ways aggregate rates hide. Post-training raises refusal most but can mix refusal with attempted answers. Activation intervention gives smaller, transferable changes.

ai-safety, multimodal, research· Added 28 Oct 2026, published 27 Oct 2026

securityweek.comarticle🛡️ Security

Vendor Key Leak Puts Data of 238,000 Denver Health Plan Members at Risk

Denver Health Medical Plan is notifying 238,083 members that vendor SquareML leaked an access key on a public website. The key was online from 27 June 2025 until it was revoked on 18 August 2026 and gave read-only access to a database of names, dates of birth, health metrics, eligibility and admission data. DHMP found no evidence of misuse and reset passwords for all accounts with access.

Threat Intel· Published and added 27 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Towards Quantum Sensing for Side-Channel Analysis

Preprint on using nitrogen-vacancy (NV) center quantum sensing for electromagnetic side-channel analysis of ICs. The authors build an NV-based RF spectrometer with 1.1 GHz real-time bandwidth and adjustable center frequency, which reads the spectrum in the time domain without Fourier transforms or frequency sweeps. They use it on RSA decryption emanations and for leakage detection on a software Number Theoretic Transform running on a Cortex-M4 microcontroller.

Hardware & RF· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

OpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents

OpenGray is a benchmark that adds tasks with known correct decisions to the OpenKBP-Opt head-and-neck dataset, including two overlap contradictions with provably incompatible dose goals and a feasible control. Four planning systems, from a rule-based script to a full LLM agent, were tested on 30 patients with Terra and Ministral 3 8B. Decision accuracy reached 95.4% and 92.1%, yet only 50% and 25% of overlap contradictions were escalated. SAGE logs of 39 radiosurgery runs showed an agent that lacked an action for stopping.

evals, agents, research· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

p-DCIM: A 28nm Probabilistic SRAM DCIM based Ising Machine for Near-Memory Context Selection in LLM-RAG Pipeline

p-DCIM is a 28 nm SRAM digital compute-in-memory macro (0.16 mm2, 0.41 mW) that works as an Ising machine for RAG evidence selection. Selection is cast as a QUBO problem, and the same MAC datapath computes embedding similarities and annealing steps. Replacing LLM reranking with it gives a selection-energy estimate over six orders of magnitude lower and cuts total energy per query by 67%, with comparable token-level F1 on the evaluated examples.

research, inference, llm-apps· Added 28 Oct 2026, published 27 Oct 2026

arxiv.orgpaper🧠 AI

AxisQ: Depth-Adaptive Channel--Frequency Quantization for Camouflaged Object Detection

AxisQ is a post-training quantization framework for camouflaged object detection (COD) that allocates activation bits by feature depth. It uses the channel domain for shallow features and the local-frequency domain for deep features, under a fixed per-layer average bit budget. It adds a boundary-aware Hessian approximation for reconstruction. On CAMO at W2A2, weighted F-measure improves 12.7% for CFRN and 33.3% for CamoFormer-P over the strongest baselines.

research, inference, multimodal· Added 28 Oct 2026, published 27 Oct 2026

securityweek.comarticle🛡️ Security

Maritime Coalition Launches Free Vulnerability Database for Ship and Port Systems

Blue Initiative is a free public vulnerability database for maritime IT and OT, built by Cydome, ClassNK, Bureau Veritas, MTS-ISAC and Rakuten Maritime. It holds nearly 30,000 entries, over 2,000 rated critical by CVSS and more than 580 known exploited. Only 37 affect ship and port products. Most entries are pulled from CISA ICS advisories and the KEV catalog and mapped to maritime systems.

other· Published and added 27 Oct 2026

arxiv.orgpaper🧠 AI

Your Wish Is My Commit: Over-Compliant Refactoring in AI Coding Agents

Your Wish Is My Commit is a controlled study of over-compliant refactoring in Codex and Claude Code, run across five models, 50 algorithmic tasks and 10 object-oriented tasks. Over 3,000 turns of repeated "refactor further" prompts, no model stopped on its own: each rewrote up to 31x the original codebase before first stopping and resumed edits after declaring the task complete. The paper defines six behavioral signals for detecting over-compliance.

coding-agents, research, evals· Added 28 Oct 2026, published 26 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Analyzing Compiler-induced Constant-time Violations with Compiler at Scale

CTGREP is a compiler-based framework that applies differential analysis across the whole Clang/LLVM compilation chain to find where, how and under which configurations compiler optimizations break constant-time cryptographic code. Applied to seven libraries, three Clang versions, six targets and thousands of configurations, it led to 48 cases fixed with developers. It also identified seven new problematic LLVM passes and bypassed existing compiler-flag mitigations.

Hardware & RF, AppSec· Added 27 Oct 2026, published 26 Oct 2026

bankless.comarticle🧠 AI

The Rise of Onchain Inference Markets

Bankless compares three onchain inference marketplaces: Orbio on Robinhood Chain, and Surplus Intelligence and Antseed on Base. Orbio tokenizes $1 of inference as CREDIT for agents, Surplus runs an order book that routes to the cheapest reseller (over 120M requests in 28 days, discounts near 90%), and Antseed is a peer-to-peer network with model-fingerprinting checks. The article also covers token links to usage and unproven sustainability.

ai-infra, agents· Added 30 Oct 2026, published 26 Oct 2026

cisa.govadvisory🛡️ Security

EPICS Base

CISA ICS advisory ICSA-26-300-01 (October 27, 2026) covers EPICS Base release 7.0.10 and earlier, with CVE-2026-114595 through CVE-2026-114598. Flaws include integer overflow, length parameter inconsistency and type confusion, allowing denial of service, memory corruption, information disclosure or remote code execution (CVSS v3.1 9.8). The fix is EPICS Base 7.0.11, with patches in epics-base and pvDataCPP pull requests.

AppSec· Added 29 Oct 2026, published 26 Oct 2026

huntress.comwriteup🛡️ Security

AI, Scripts, Operator: Inside the ConnectWise Attack

Huntress analyzes Entra sign-in and audit logs from the ConnectWise Cloud Backup credential abuse of 15 October 2026 to judge whether a script, a person or an LLM agent drove it. It found a thread-pool spray, trial-and-error credential planting with a retry added within 55 seconds, and pilot-then-batch targeting. Huntress rates LLM involvement low to medium on its own data and medium to high with Microsoft's Storm-0940/ARTEX attribution. It ends with detections for service principal role self-assignment and vendor app baselining.

Threat Intel, Blue Team & Detection, Identity & Access, AI Security· Published and added 26 Oct 2026

protos.comarticle🛡️ Security

Keystone to destroy almost 19,000 wallets after device key leak

Keystone confirmed a breach of Shopify customer records (about 26,000 plus 13,000 incomplete orders), in which the attacker also took the WebAuth key used to verify device authenticity. It will destroy almost 19,000 unshipped wallets and issue a new key. Foundation Passport phishing emails (over 20,000) came from compromised Cloudflare API keys, and old WooCommerce database copies kept personal data past the stated 60-day deletion.

Threat Intel, Hardware & RF· Published and added 26 Oct 2026

latent.spacetalk🧠 AI

Supabase’s Plan for a Billion AI-Built Apps

Latent Space interview in which swyx talks with Supabase co-founders Paul Copplestone and Ant Wilson about backends for software built by AI agents. Topics include Supabase Compute for running workloads next to the database, Multigres for highly available Postgres (private alpha), the Turso acquisition, declarative schemas, and durable workflows. The page has only show notes and chapters, recorded ahead of Supabase Select 2026.

ai-infra, agents· Published and added 26 Oct 2026

arxiv.orgpaper🛡️ Security

Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models

REVA (REal-time Vulnerability Analysis) is an LLM-based vulnerability detector that screens each new function in one forward pass. It feeds the model a pre-computed module threat model, lightweight static analysis findings and call-graph data, then reads the model's internal representations with a trained probe. On PrimeVul's held-out test set with GLM-5.3-Flash it reaches 60.0% accuracy in about one second per function, matching the agentic VulTriage (59.2%) while over 250 times faster.

AI Security, AppSec· Added 28 Oct 2026, published 26 Oct 2026

x.comthread🛡️ Security

Benjamin👨‍💻 (@Hislordship_9) on X

Thread on Forever Security's finding that a planted Markdown "Engineering Work Guidelines" file in ~/Downloads made Codex add a "project-tools" MCP server to ~/.codex/config.toml. The server ran npm install function-color, a known malicious package, and started a child session with --dangerously-bypass-approvals-and-sandbox. Codex complied in over 90% of the firm's tests; Claude Code, via a CLAUDE.md setting ANTHROPIC_BASE_URL, about half. Advice: don't start agents in Downloads, review instruction files, and diff agent config.

AI Security, Supply Chain· Added 27 Oct 2026, published 26 Oct 2026

cisa.govarticle🛡️ Security

CISA Publishes Significant Updates to ScubaGear and ScubaGoggles

ScubaGear v2.0 and ScubaGoggles v1.1.0 are CISA's updated SCuBA assessment tools for Microsoft 365 and Google Workspace secure configuration baselines. ScubaGear now uses direct REST API calls, adds Power BI coverage, a consolidated Security Suite baseline and app severity scoring. ScubaGoggles adds a GUI, Policy API integration and Gemini controls. The release supports BOD 25-01 compliance.

Cloud & Infra, GRC· Added 29 Oct 2026, published 26 Oct 2026

ubicloud.comwriteup🧠 AI

Fixing Tool-Call Accuracy in vLLM

Ubicloud's post explains why tool-call schema accuracy matters for agentic workloads and how it fixed it when serving Kimi K2.6 and DeepSeek V4 Flash. With vLLM 0.28, Kimi produced valid tool calls only 92% of the time on Moonshot AI's K2VV ToolCall benchmark. Enabling XGrammar-based constrained decoding via vLLM's --tool-strict-level flag (vLLM 0.31) raised schema accuracy to 100%.

inference, mcp, evals· Added 27 Oct 2026, published 26 Oct 2026

brown.eduarticle🧠 AI

Brown student maps the hidden global labor powering AI

Brown University undergraduate Cunyan Ma built an interactive map linking technology companies and their intermediaries to data workers around the world, with the university's Center for Technological Responsibility, Reimagination and Redesign. The map combines existing data worker databases, Ma's own data collection and news reports on working conditions. It aims to show "AI colonialism" at scale, beyond anecdotal accounts. The page text ends early.

training, ai-policy· Added 27 Oct 2026, published 26 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Cryptanalysis and Repair of "Decentralized Multi-authority ABE for NC$^1$ from BDH"

Cryptology ePrint 2026/2642 presents a plaintext-recovery attack on the DBDH and CBDH variants of the Datta, Komargodski and Waters multi-authority ABE for NC1 (Journal of Cryptology, 2023). It needs one corrupt authority and two users, and succeeds with probability one in the static model. The flaw is an invalid extension of the Rouselakis-Waters LSSS matrix-normalization lemma. The paper also attacks two Datta-Pal (PKC 2023) attribute-based inner-product schemes and proves repaired versions secure in the random oracle model.

other· Published and added 26 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Private Information Retrieval with Accountability at Erasure-Optimal Server Redundancy

SynTrace is a single-round compiler that adds accountability to linear private information retrieval (PIR). The client mixes the retrieval query with m audit queries, so audit syndromes identify up to d deviating servers among t colluding ones before reconstruction. The paper proves perfect query privacy and zero false identification within the threshold. For Shamir-based PIR it needs k=t+d+1 servers. For a 32 KiB record from a 1 GiB database it uses 2.25 MiB, against 8.96 MiB for the Eriguchi, Kurosawa and Nuida (TCC 2022) homomorphic-MAC construction.

other· Published and added 26 Oct 2026

x.comthread🛡️ Security

alex lee (@alexlee20122022) on X

Gheist is a GitHub campaign disclosed by Wiz in October 2026. Stolen tokens push ci-sync-XXXXXX branches with a sync-check workflow that dumps repo secrets base32-encoded to evade log masking, fetches the logs via API, then deletes the run. 13,500+ branches and 850+ accounts were hit since 15 September. Public repos are protected by the approval hold; private and Enterprise repos are not. The thread lists IOCs (.gdmp_pat files, "gheist" user agent, "ci: sync config" commits) and rotation steps.

DevSecOps, Threat Intel, Supply Chain· Added 26 Oct 2026, published 25 Oct 2026

wiz.iowriteup🛡️ Security

Gheist: Attempted Scaled Abuse of Stolen GitHub Tokens Stumbles

Gheist is a campaign tracked by Wiz Research since 15 September 2026 that uses stolen GitHub tokens to push a sync-check workflow on ci-sync-* branches in every reachable repository. The workflow prints base32-encoded secrets into logs, which the tool downloads through the GitHub API and then deletes. Over 13,500 branches from 850+ accounts were recovered. The post covers the two tool variants, a buggy self-hosted runner payload, GitHub's approval hold (which does not cover private repositories), overlaps with other campaigns, hunting queries, IOCs and hardening steps.

Threat Intel, DevSecOps, Blue Team & Detection· Published and added 25 Oct 2026

x.comthread🧠 AI

Syb (@DegenOfWallSt) on X

Nanbeige4.3-33B is a 33.1B dense, Llama-style open model under Apache-2.0, released with a base model on Hugging Face. In Nanbeige's own table it beats Qwen3.8-27B on Terminal-Bench 2.1 (80.9 vs 73.0), DeepSWE (65.5 vs 42.5) and Automation Bench, but trails on SWE-Bench Pro, GDPval and GPQA Diamond. BF16 weights are about 66 GB, split across 4 GPUs in the vLLM and SGLang examples. No independent evals exist yet.

models, coding-agents, evals· Added 26 Oct 2026, published 25 Oct 2026

theblock.coarticle🛡️ Security

Keystone customers say breach exposed data the hardware wallet maker promised to delete

Keystone, a hardware wallet maker, disclosed on 25 October 2026 that an attacker accessed its Shopify-based store, detected 20 October and confirmed 23 October. Customer names, contact details, shipping addresses and order details were taken. Keystone says no payment data, recovery phrases or keys were exposed. Customers on X say their data was held despite a 180-day deletion pledge. The piece lists 2026 leaks at Trezor, SafePal and Ledger.

Threat Intel· Published and added 25 Oct 2026

arxiv.orgpaper🛡️ Security

Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine

Open bilingual (Russian and UK English) benchmark of five open pseudonymisation tools and a regex baseline, plus a new engine built on the two strongest tools. On a held-out set of 1,000 synthetic documents per language, the best existing tools leave a whole personal value visible in 61% (Russian) and 58% (UK) of documents. The engine does so in 0.3% and 0.2%. Russian name restoration reaches only 94.6%, below the 99% threshold. Real documents were not tested.

AI Security· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper🧠 AI

Reversible Pseudonymisation of Documents Sent to External LLMs: an Open Bilingual Benchmark and an Engine

This paper presents an open benchmark of five existing pseudonymisation tools and a regex baseline on Russian and UK English documents, plus an open engine built on the two strongest tools. On a held-out set of 1,000 synthetic documents per language, the best existing tools leave a whole value visible in 58 to 61% of documents. The engine does so in 0.2 to 0.3%. Russian name restoration reaches only 94.6%, below the 99% threshold. Real documents were not tested.

evals, llm-apps, research· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper🧠 AI

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

InteractiveWorld is an environment for closed-loop interaction between an AI assistant and a simulated human agent who sees the scene, follows instructions and acts independently. InteractiveBench, built on it, has 120 multi-turn tasks in six categories scored by verifiable, state-based rewards. Across 12 frontier MLLMs, the best model, Claude Fable 5.1, reaches at most 20% on long-horizon Guidance and 25% on Planning tasks.

evals, multimodal, research· Added 27 Oct 2026, published 25 Oct 2026

arxiv.orgpaper🧠 AI

DRILS: Dependency-based Requirement Change Impact Analysis Using LLMs

DRILS is an LLM-based agentic framework for requirements change impact analysis. It uses multiple agents to generate candidate impact sets, with an LLM-as-a-judge promoting diversity in selection. It adds RE-RAG, a tuned retrieval technique, and a requirement dependency graph as a knowledge source. On three curated datasets it reaches 87.1% recall, 76.3% precision and 81% F1 at lower cost than baselines. The authors release the datasets.

research, agents, llm-apps· Added 27 Oct 2026, published 24 Oct 2026

x.comthread🧠 AI

Big Bull (@BIGBULLapp) on X

5ire is a desktop AI assistant and MCP client that connects to OpenAI, Anthropic, Google, Mistral, Grok, DeepSeek and Ollama from one window. It has a local knowledge base and tool calls over Model Context Protocol. The tools feature needs Python, Node and uv installed because it runs a local MCP server; without them it works only as a chat client.

mcp, llm-apps· Added 25 Oct 2026, published 24 Oct 2026

arxiv.orgpaper🛡️ Security

Enhancing LLM-Based Vulnerability Detection via Representation-Aware Logical Ensemble

RALE (Representation-Aware Logical Ensemble) is a method for detecting vulnerabilities in C source code with LLMs trained on different code representations: raw source, Abstract Syntax Trees and Control Flow Graphs. The authors show the representations suit different vulnerability classes, and combine the models with explicit logical rules and majority voting. Single-representation models reach up to 73% F1, while the ensemble reaches 78%.

AI Security, AppSec· Added 28 Oct 2026, published 24 Oct 2026

arxiv.orgpaper🧠 AI

Enhancing LLM-Based Vulnerability Detection via Representation-Aware Logical Ensemble

RALE (Representation-Aware Logical Ensemble) is a method for LLM-based vulnerability detection in C code. The authors train LLMs on raw source code, Abstract Syntax Trees and Control Flow Graphs, and find each representation works best for certain vulnerability classes. Combining the models with explicit logical rules and majority voting raises F1 from at most 73% for a single model to 78%, with gains in accuracy, precision and recall.

research, training· Added 28 Oct 2026, published 24 Oct 2026

arxiv.orgpaper🧠 AI

ZipFusion: Fusing Lossless KV Decompression with Attention for Efficient LLM Decoding

ZipFusion is a lossless KV cache compression scheme whose attention kernel reads the compressed cache directly and rebuilds the original values in registers with simple bit operations, so no separate decompression pass is needed. It also reassigns the memory freed by compression across layers to hold more KV cache. Built on FlashInfer and integrated with SGLang, it gives about 1.25x decode attention speedup on an H100 and up to 26.3% higher decode throughput at 8K context than uncompressed SGLang. It reaches up to 2.76x the throughput of the best lossless KV compression baseline.

inference, research· Added 27 Oct 2026, published 24 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network

Extraction meets Distillation is an IACR ePrint paper (2026/2628, CSCML 2026) that combines cryptanalytic weight-direction extraction with label-based distillation to reconstruct fully connected neural networks. It adapts a ReLU extraction implementation to Leaky ReLU and proves conditional bounds for direction recovery and sign selection. On CIFAR-10 victims, reconstructed models reach 56.40% and 58.29% agreement. It separates label requests from privileged access and notes that prediction agreement does not identify parameters.

AI Security· Added 26 Oct 2026, published 24 Oct 2026

opensourcemalware.comwriteup🛡️ Security

Brotlipocalypse

Brotlipocalypse is an OSM Security post (24 October 2026) on CVE-2026-111497, an out-of-bounds write in the google/brotli C decoder (1.0.3 through 1.2.0). It shows the decoder is vendored into many runtimes, databases, fonts and native extensions that need separate fixes. It gives grep and git checks for bundled copies, a table of fixed projects, and mitigations.

Supply Chain, AppSec· Published and added 24 Oct 2026

eprint.iacr.orgpaper🛡️ Security

The Exact Bit Security of Hash-Based Signatures

The Exact Bit Security of Hash-Based Signatures is a 2026 IACR ePrint paper that analyses XMSS with 128-bit digests and SLH-DSA-128s in the random oracle model, with proofs formalised in Lean4. Strong unforgeability comes to 127 bits under most accounting modes but only 122 bits if just direct random oracle queries are counted. The authors give matching attacks, and show how resource accounting changes the result.

other· Added 26 Oct 2026, published 24 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Provable Security of SHA-256-Based LMS Revisited in the Ideal-Cipher Model

Provable Security of SHA-256-Based LMS Revisited in the Ideal-Cipher Model is an October 2026 ePrint paper by Chun Guo, Hao Cheng, Bart Preneel and Meiqin Wang. It shows forgery attacks on LMS_SHA256_M32 and LMS_SHA256_M24 that exploit Merkle-Damgård structure, so the Katz and Fluhrer random-oracle bounds do not apply. It proves ideal-cipher-model bounds: about 256 minus log2 of the block count for M32, and a minimum of two terms for M24.

other· Added 26 Oct 2026, published 24 Oct 2026

arxiv.orgpaper🧠 AI

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

FORK is a reward for rubric-based reinforcement learning that jointly optimizes recall and a new precision objective. Precision requires each unit of a response to be necessary (rubric-driven necessity credits) and factually correct (a grader). Rubric-coverage rewards otherwise produce verbose, less accurate responses. FORK keeps similar coverage with shorter outputs, raising win rate against the base policy from 10.6% to 68.0% on RubricHub-Medical and from 22.1% to 74.1% on HealthBench.

training, research· Added 27 Oct 2026, published 24 Oct 2026

x.comthread🧠 AI

EveryDev.ai (@EveryDevAi) on X

ToolUniverse, from ScientistTools, is an open-source (Apache-2.0) toolkit that gives any LLM one interface to more than 1,000 scientific tools, models and databases such as PubMed, UniProt and ChEMBL. It ships a native MCP server, a Python SDK and a tu CLI, plus 68 pre-built agent skills. The post says it works with Claude Code, Cursor, Gemini CLI and Windsurf.

mcp, agents· Published and added 24 Oct 2026

socket.devwriteup🛡️ Security

New Evidence Shows LiteLLM Secret-Stealing Workflows Ran 11 Days Before Supply Chain Attack

Socket's Threat Research team reports that malicious cache.yml workflows ran in the BerriAI/litellm repository on 10 and 12 October 2026, eleven days before the 21 October release attack that published litellm==1.107.0. Each commit pushed to a short-lived ci-tmp-<hex> branch, then deleted it, sending base64-encoded CI secrets to webhook.site. Evidence comes from Actions metrics and environment deployment records; 20 secret names were exposed.

Supply Chain, DevSecOps, Blue Team & Detection· Published and added 23 Oct 2026

aikido.devadvisory🛡️ Security

Python packages are also vulnerable to the Node2Shell Brotli flaw (CVE-2026-111497)

Python2Shell is the Python-side impact of CVE-2026-111497 (Node2Shell), a Brotli decoder flaw (CVSS 4.0 9.2) in DecodeBlockTypeAndLength() that mixes an unchecked return value with an out-of-bounds write. Brotli 1.2.0 and earlier, and brotlicffi 1.2.0.x, are affected through urllib3, requests, httpx, aiohttp and Scrapy. Fixes are Brotli 1.2.1 and brotlicffi 1.2.1.0; as of 23 October 2026 advisory databases do not map the CVE to either package. The post lists checks and workarounds.

AppSec, Supply Chain· Published and added 23 Oct 2026

arxiv.orgpaper🧠 AI

Deletion, Substitution, Repair and Transplant: Component Attribution in BARBICAN, a Layered Prompt-Injection Gateway for MCP

The paper analyses BARBICAN, a fail-closed prompt-injection gateway for MCP tool mediation, using deletion, substitution, repair and transplant experiments. Its arbitration classifier ran on tokenizer-mangled text for a whole evaluation. Fixing that raised AUC from 0.392 to 0.855 while system recall fell from 80.67% to 80.34%. The band it receives is 96.82% malicious. The authors argue ablation figures need the band's class balance and substitution baselines.

evals, research, mcp· Added 27 Oct 2026, published 23 Oct 2026

endorlabs.comarticle🛡️ Security

ADLC Security Best Practices for Teams Shipping with Coding Agents | Endor Labs

ADLC Security Best Practices is an Endor Labs guide to controlling what AI coding agents can access, run, install and ship. It covers inventorying agents and MCP servers, sandboxing, pre-execution hooks instead of AGENTS.md rules, install-time package checks against slopsquatting and malware, reachability-based triage of agent PRs, and CI/CODEOWNERS protections. A five-step worked example and coverage metrics are included.

AI Security, Supply Chain, DevSecOps· Published and added 23 Oct 2026

arxiv.orgpaper🧠 AI

What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design

This paper studies experience reuse for LLM agents that optimize ligands in protein pockets by editing and docking. Using the full log of one agent run over CrossDocked2020 test-set pockets, it tests whether keys in an experience base recur on unseen pockets and separate improving from worsening edits. The separation is largely explained by molecule size change, action and round, not the target. The authors conclude a base may better prioritize an agent's own proposals for docking than prescribe what to build.

research, agents· Added 26 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🧠 AI

Standing on Open Shoulders: Regional Fine-Tuning of Open-Weight Camera-Trap Models for UK Wildlife with Modest Data and Compute

DeepFaune-UK is a fine-tune of the open DeepFaune camera-trap classifier on 28 UK classes, paired with MegaDetector v6. On 20,212 MammalWeb images it reached 88.8% strict accuracy against 56.5% (DeepFaune v1.5.0) and 59.0% (SpeciesNet). Re-applying the recipe to the DINOv3-based classifier gave 90.6%. Fine-tuning on about 150 crops per class matched full-data out-of-distribution accuracy, and a DINOv2 run took about 22 minutes on under 4 GB of GPU memory.

research, training, multimodal· Added 26 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🛡️ Security

On Task, Off Track: Benchmarking LLM and Agent Robustness to Near-Target Prompt Injection

NTBench (Near-Target Benchmark) tests LLM and agent robustness to near-target prompt injection, where injected instructions steer a response toward a plausible but incorrect or harmful outcome instead of abandoning the task. It builds reference-guided target-instruction pairs on existing datasets, with human validation, and evaluates seven LLMs on ten language datasets and two agent benchmarks. Attack success rose 9.3 to 35.8 points (incorrect targets) and 1.7 to 17.3 points (harmful targets) over fixed-target baselines.

AI Security· Added 26 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🧠 AI

DRIVE: Fine-tuning via Data Contribution- and Diversity-aware Weighting with Prior Regularization

DRIVE is a per-sample weighting framework for single-stage fine-tuning when the source pre-training data is unavailable. It uses one differentiable objective: Shapley additivity splits each sample's contribution into anti-forgetting and adaptation parts, a covariance-based diversity term reshapes them, and a sample-characteristic prior stabilizes them. The authors prove better stability-plasticity guarantees than existing weighting schemes and report better performance, faster convergence and more robustness.

training, research· Added 26 Oct 2026, published 23 Oct 2026

arxiv.orgpaper🧠 AI

Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues

ProfileSim is a profile-driven user simulator for financial marketing outbound calls. It models user profiles (demographics, Big Five traits) and business profiles (intents reverse-engineered from real call logs). The base model is fine-tuned on real voice dialogues, then refined with GRPO using dialogue-level and utterance-level rewards. Against other user generators it scores highest on colloquial naturalness and profile adherence, and lowest agent score on long-tail intents, with shorter utterances at comparable business compliance.

research, training· Added 26 Oct 2026, published 23 Oct 2026

opensourcemalware.comwriteup🛡️ Security

Python Packages Vulnerable to Node2Shell

Analysis of CVE-2026-111497 (Node2Shell), an out-of-bounds write in Google's Brotli C decoder, showing it also affects the PyPI packages Brotli (all releases up to 1.2.0) and brotlicffi (up to 1.2.0.2). The author diffed the 1.2.0 and 1.2.1 sdists and confirmed the behaviour with AddressSanitizer. Fixes are Brotli 1.2.1 and brotlicffi 1.2.1.0, both patched without release notes. No advisory database lists either package yet.

AppSec, Supply Chain· Published and added 23 Oct 2026

arxiv.orgpaper🧠 AI

MPQ: A Message-Passing View of Post-Training Quantization

MPQ (Message-Passing Quantization) is a post-training quantization method that treats row-wise PTQ as posterior inference over discrete codebooks. It keeps soft posteriors across weight blocks using vector approximate message passing, then refines a hard-decision initialization with exact block coordinate descent. Tested at 2-bit lattice and 3- and 4-bit scalar quantization on Llama, Qwen and Mistral models, it improves perplexity and zero-shot accuracy over GPTQ-style baselines.

research, inference· Added 26 Oct 2026, published 23 Oct 2026

huggingface.cowriteup🧠 AI

Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox

ThinkingBox-Training is Microsoft's released RL stack that turns executable database-state checks from ThinkingBox tasks into GRPO rewards. Fifty GRPO steps on 187 curated tasks raised Qwen3.8-27B pass@1 from 51.70% to 60.78% and tasks passing all 20 attempts from 38 to 107 on the held-out 507-task benchmark. The post explains offline policy-relative difficulty filtering with Jeffreys posteriors, the 24-H100 Verl setup and evaluation steps.

training, agents, evals· Published and added 22 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Mímir: A Stateless Private Search Engine

Mímir is a cryptographic protocol for stateless semantic private search over highly dynamic public databases. It uses homomorphic ciphertext switching, relies on (Ring) Learning with Errors, and needs no offline communication. Against Tiptoe it matches search quality with 84x less per-query communication (0.24 MiB). Against PACMANN it raises quality from 76% to 81% of non-private search, with a 9.54 MiB one-time cost instead of 2.68 GiB, but is 2.1x slower.

other· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation

CausalCoT is an inference framework that splits a problem into a directed acyclic graph of atomic sub-questions and evaluates each node in an isolated context holding only its direct causal parents. This removes attention paths to non-parent content, so intermediate steps drive the answer rather than leaking from global context. It keeps benchmark accuracy competitive and raises causal sensitivity of reasoning steps by 12 points on average, up to 21, over the strongest baseline. The graph also allows test-time corrections that propagate downstream.

research, prompting· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

Progress Probes $P^2$: Lightweight Runtime Monitoring for Vision-Language-Action Models

Progress Probes (P^2) trains linear probes on a vision-language-action model's own activations, using demonstrations, to estimate task progress, then flags executions that deviate from expected progress. Tested on the open-source pi0.5 across simulated and real-world manipulation tasks, it matches or beats VLM-based monitors and failure-data-trained methods at failure detection, without an external foundation model.

research, multimodal· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

Who Is Sycophantic to Whom? Confident LLMs, Human Deference, and the Collapse of Trust Calibration

This paper studies reverse sycophancy: whether users bend toward a confident, consistent, wrong LLM. In a within-subjects experiment, 32 participants learned science topics from five GPT-5-mini assistants with 0 to 100% of facts replaced by falsehoods. Scores fell from 7.4 to 2.9 out of 10, planted falsehoods were chosen on 60% of falsified items against 11% of correctly taught ones, and confidence stopped tracking correctness. It introduces a baseline-corrected Human Deference Index.

research, ai-safety, evals· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

Rethinking Sequence Compression with Test-time Regression

TTR-Compressor is a sequence compression method that treats input tokens as a test-time regression problem. The regression is learned end-to-end by backpropagation, and its coefficients are solved in closed form in the forward pass to give the compressed representation. As a block-wise sparse attention compressor it improves RULER over attention-based compressors by a large margin. As a visual token merger for multimodal LLMs it beats the MLP merger and matches it with 55.6% fewer visual tokens.

research, multimodal· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks

This empirical study benchmarks recent LLMs against fine-tuned encoder-decoder models on knowledge graph-to-text generation, using reference-based metrics and graph-grounded, reference-free LLM-based evaluation validated against human annotations. Recent LLMs narrow or close the gap on reference-based metrics and do better on graph-grounded ones. Prompted models make fewer contradictions and triple omissions, and fine-tuned models' errors grow faster with graph size.

research, evals· Added 24 Oct 2026, published 22 Oct 2026

arxiv.orgpaper🧠 AI

From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries

This paper studies evidence-grounded health summarization for menstrual health monitoring. It combines structured evidence conditioning with RAG in a prompt-based constrained generation framework, and scores 4,500 summaries from three LLMs with NLI, atomic factuality metrics and readability measures. Grounding constraints improved uncertainty preservation and generally kept or improved faithfulness against retrieved evidence, while omission effects varied by model. Clinical alignment came with harder reading and more medical terminology.

research, evals, llm-apps· Added 24 Oct 2026, published 22 Oct 2026

deepmind.googlearticle🧠 AI

Beyond tree cover: mapping the world’s forest types

Forest Typology (ForTy) 2020 is a global 10-meter map from Google DeepMind, Google Research, WRI and IIASA. It sorts land into six FAO-based classes: primary, naturally regenerating, planted, plantation, tree crops and agroforestry, and other land. The model uses AlphaEarth Foundations embeddings and about 1.7 million labeled locations. It was 90% accurate on forest type across 9,000+ expert-checked sites. An early 2017 to 2025 time series is on Earth Engine.

models, multimodal· Published and added 22 Oct 2026

securityweek.comarticle🛡️ Security

Signal Vulnerability Lets Malicious Callers Block Hang-Ups

CVE-2026-113380 (CVSS 9.3) is a flaw in RingRTC, the WebRTC-based library behind Signal voice and video calls. A remote peer can flood the call's finite state machine event queue, so the victim's hang-up waits behind junk and audio and video tracks stay live. Fixed in RingRTC 2.72.0 on 4 September; a researcher published details and a conceptual PoC afterward.

Mobile Security, AppSec· Published and added 22 Oct 2026

arxiv.orgpaper🧠 AI

RIFT: KV Cache Compression for Draft Models with Complementary Compressibility Training

RIFT is a family of selection-based KV cache compression strategies for speculative-decoding draft models. It targets "decode staleness", where prefill-focused selection loses relevance as output grows, by balancing prefill information with recent generated tokens, refreshing the selection adaptively, and training drafters with sparse attention masks. Qwen3.5-4B drafting for Qwen3.5-122B keeps over 98% of full-cache acceptance length at 32K input, 4K output and an 8K KV budget.

research, inference· Added 23 Oct 2026, published 22 Oct 2026

eprint.iacr.orgpaper🛡️ Security

The Good, the Bad, and the Noisy: A Systematic Analysis of Ring-Oscillator-Based Noise Generators

This IACR ePrint paper (2026/2597) systematically compares ring-oscillator-based additive noise generators, a hiding countermeasure against side-channel attacks. Experiments show many existing designs ignore output amplification and the risk of the noise being filtered out, so they lower signal-to-noise ratio too little. The authors give a guideline on inverter chain length, output amplification and frequency randomization, and build a tailored generator for an AES implementation that outperforms prior designs.

Hardware & RF· Added 24 Oct 2026, published 22 Oct 2026

securityweek.comarticle🛡️ Security

Cisco Patches 34 Vulnerabilities Across Multiple Products

Cisco's October 21, 2026 patch batch fixes 34 vulnerabilities in Expressway Series, IOS XR, Snort 3 and Unified Communications products. The critical Expressway RCE (CVE-2026-76466) lets an attacker reach the database service and run commands as root; it is fixed in X15.5.20. Snort 3 fixes ship in 3.12.4.0 and several Cisco security products. Cisco knows of no exploitation in the wild.

AppSec, Cloud & Infra· Published and added 22 Oct 2026

x.comadvisory🛡️ Security

lee1981 (@lee1981b) on X

CyberForge CVE of the Day #084 analyses CVE-2026-76466, a CVSS 9.8 flaw in clustered Cisco Expressway-C and Expressway-E. Persistent database cookies and weak client-certificate validation allow root OS command execution over the network. The fix is X15.5.20 (X14 and earlier must migrate), with no workaround. It adds a per-peer SOC investigation trail, reachability checks and exposure status from CISA SSVC, KEV and EPSS.

Blue Team & Detection, Cloud & Infra· Added 24 Oct 2026, published 22 Oct 2026

metr.orgarticle🧠 AI

Red-Teaming OpenAI's Internal Agent Monitoring Systems

METR's post summarises a three-week pilot (21 July to 11 August 2026) in which a METR and a Redwood Research employee red-teamed OpenAI's internal misalignment monitoring system with deep codebase access. They estimated 75-94% of agentic Responses API traffic was monitorable, and found gaps such as unmonitored compaction events, RL training runs, and headers that disable monitoring. OpenAI says all production issues are patched; METR lists five design ideals for monitors.

ai-safety, agents, ai-policy· Added 29 Oct 2026, published 22 Oct 2026

metr.orgwriteup🛡️ Security

Red-Teaming OpenAI's Internal Agent Monitoring Systems

METR and Redwood Research summarize a three-week pilot red-team (21 July to 11 August 2026) of OpenAI's internal asynchronous misalignment monitoring system. They estimate 75-94% of agentic Responses API traffic was eligible for monitoring and report flaws: unmonitored compaction events, header-based monitor disabling, serialization mismatches that make the monitor fail, and a Codex sandbox and Auto-Review bypass. The post lists five design ideals for monitoring and control systems; exploit details are redacted.

AI Security· Added 29 Oct 2026, published 22 Oct 2026

soliditylang.orgadvisory🛡️ Security

Yul Optimizer Knowledge Base Stale Bookkeeping Bug

Solidity advisory on a Yul optimizer bug in the KnowledgeBase, present in versions 0.8.19 to 0.8.37 and fixed in 0.8.38. Stale cached address offsets let LoadResolver and EqualStoreEliminator treat coinciding memory or storage slots as distinct, so loads return outdated values or needed stores are dropped. It includes a pure-Solidity reproducer for --via-ir, a Sourcify scan with no differing bytecode, and checks for deployed contracts. Rated low severity.

AppSec· Published and added 22 Oct 2026

arxiv.orgpaper🧠 AI

IFC-MCQ: Automatically Generating Multiple-Choice Benchmarks for Evaluating LLM Agents on IFC Data Retrieval

IFC-MCQ is a method that automatically generates multiple-choice benchmarks from Industry Foundation Classes (IFC) building-model files, so answers can be graded by exact option-set match instead of human or LLM review. Its taxonomy has 15 categories and 36 subtypes in four groups, with answer keys from the file and distractors from file values or rules. Two agentic setups, tool-based and code-based retrieval, showed category-specific failures and variation by IFC model and interface.

evals, agents, research· Added 23 Oct 2026, published 21 Oct 2026

x.comthread🧠 AI

SpyTech Ai (@RizeOnline) on X

XiaoZhi ESP32 is an open-source, MIT-licensed firmware stack that turns ESP32 boards into MCP-based voice chatbots using models such as Qwen and DeepSeek. It streams Opus audio over WebSocket or MQTT + UDP through ASR, LLM and TTS, adds offline ESP-SR wake words, and uses device-side MCP to drive speakers, LEDs, servos and GPIO. It supports 138 board directories and builds with ESP-IDF 6.0.1 or newer.

mcp, multimodal, llm-apps· Added 23 Oct 2026, published 21 Oct 2026

arxiv.orgpaper🧠 AI

SIM-UT: A User Simulation based Evaluation Framework for Medical Triage Chatbots

SIM-UT (Simulation of User Behaviour for Triage) is a multi-turn, simulation-based method for finding failure modes in LLM medical triage chatbots. It was applied to three WhatsApp health chatbots (India, South Africa, Kenya) across 5,000+ multilingual simulated turns, comparing MedGemma with ChatGPT and Claude. The main finding is de-escalation risk: agents that first flagged emergencies agreed with users who minimised symptoms, such as vaginal bleeding in pregnancy.

evals, ai-safety, research· Added 24 Oct 2026, published 21 Oct 2026

huggingface.coarticle🧠 AI

NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required

NVIDIA Kumo Relational is a pre-trained relational foundation model that predicts outcomes such as churn or fraud directly on multi-table databases through in-context learning, using up to 10,000 context examples and no task-specific training. NVIDIA reports it beats supervised relational deep learning and XGBoost pipelines across 41 tasks on 15 databases, and beats AutoGluon by 8% MRR on SAP SALT. Code is Apache 2.0, weights are on Hugging Face.

models, research, evals· Published and added 21 Oct 2026

bankless.comarticle🛡️ Security

Coinbase's Plan for a Quantum-Safe Bitcoin

Bankless summary of Coinbase's October 2026 proposal for making Bitcoin quantum-safe. It covers upgradeable address designs (BIP-360 P2MR, P2TRv2, hybrid addresses), four candidate signatures (ML-DSA, SLH-DSA, FN-DSA, SHRINCS) with size and stateful-key-reuse trade-offs, a five-stage migration plan, and a separate track for dormant coins with exposed public keys such as Satoshi's.

Blockchain· Published and added 21 Oct 2026

endorlabs.comwriteup🛡️ Security

LiteLLM 1.107.0 Compromised: Python Startup Hooks Steal Cloud, AI, and Proxy Credentials | Endor Labs

litellm 1.107.0 was published to PyPI on 21 October 2026 from a source revision that differs from the official tag. One line in the Maturin config (data = "cook") installs cook.pth, cook.py and sitecustomize.py, which run on every Python start. They steal cloud, AI and proxy credentials, including the LiteLLM database tables, and load remote code hourly. The post gives IOCs, a five-step response plan and hardening advice.

Supply Chain, Malware & RE, DevSecOps· Published and added 21 Oct 2026

blog.trailofbits.comarticle🧠 AI

Your AI agent fixed the bug, but what else did it change?

Trail of Bits releases patching-bugs and regression-hunt, two agent plugins built with OpenAI through Patch the Planet. patching-bugs reproduces bugs, writes fixes and runs a three-arm proof; regression-hunt traces diffs to real interfaces, confirms with live PoCs and a fresh-context replay. A review of 130+ merged PRs found 21 regressions, and regression-hunt gave 25% fewer false positives than a baseline Codex prompt.

coding-agents, agents, evals· Published and added 21 Oct 2026

blog.trailofbits.comarticle🛡️ Security

Your AI agent fixed the bug, but what else did it change?

Trail of Bits releases patching-bugs and regression-hunt, two Codex plugins from the Patch the Planet initiative with OpenAI. A review of 130+ merged patches confirmed 21 regressions (none broke a security protection). In preliminary tests regression-hunt gave 25% fewer false positives than a baseline Codex agent. Design uses live PoCs, strict schemas, a three-arm proof, and project THREAT_MODEL.md and PATCHING_GUIDELINES.md files.

AI Security, AppSec· Published and added 21 Oct 2026

stepsecurity.iowriteup🛡️ Security

litellm 1.107.0 Compromised on PyPI: Backdoored Wheels Drop a Credential Stealer and an Hourly Remote Code Loader

litellm 1.107.0 was published to PyPI on 21 October 2026 with all seven wheels backdoored through an injected `data = "cook"` maturin build line. The wheels drop cook.pth, cook.py and sitecustomize.py, which run on every Python start. They install a "privcollect" credential stealer (browser, SSH, cloud, AI coding tool and LiteLLM proxy database secrets, sent to litellm.dev) and an hourly GitHub dead-drop remote code loader. The post gives IOCs, detection commands and recovery steps.

Supply Chain, Malware & RE, Blue Team & Detection· Published and added 21 Oct 2026

socket.devwriteup🛡️ Security

LiteLLM PyPI Package and Docker Images Compromised to Steal Cloud and AI Credentials

LiteLLM 1.107.0 on PyPI and GHCR images shipped Python startup hooks (cook.pth, sitecustomize.py) that steal cloud, SSH, browser and AI-tool credentials, including LiteLLM proxy database credentials. Image build provenance recorded a lookalike Berri-AI/litellm source repository. The post decodes the payload, encrypted exfiltration and GitHub-driven remote loader, and lists containment steps, MITRE ATT&CK mappings and IOCs.

Supply Chain, Malware & RE, Threat Intel· Published and added 21 Oct 2026

huntress.comwriteup🛡️ Security

Amazon-Themed ClickFix Campaign Serves Up Finger-Licking Malware

Huntress analysis of an Amazon-themed ClickFix campaign that used a Google sponsored result, a fake Amazon login on Google Sites and a fake CAPTCHA to make victims run the Windows finger utility. The .plan script drives IronPython, a Cyrillic-substituted Base64 Python loader, Doina, a Node.js stage, Lumma Stealer via sRDI, and a pirated NetSupport RMM. It lists C2 domains and gives detection tips (aclk/gclid markers, blocking the Run dialog).

Threat Intel, Malware & RE, Blue Team & Detection· Published and added 21 Oct 2026

layerfs.aitool🧠 AI

LayerFS: The filesystem for AI coding agents

LayerFS is a serverless, versioned filesystem for AI coding agents. Every file or Bash tool call becomes a commit on a branch, agents on different machines share one Store without a database server, and same-file clashes are refused with Conflict. Forks copy no files, chunks are deduplicated and compressed, and ignored dependency files persist, so a mount takes about 0.05 s against about 5 minutes of reinstalling. The page gives vendor claims and no benchmarks or docs.

coding-agents, ai-infra, agents· Added 22 Oct 2026, published 21 Oct 2026

hirundo.iowriteup🧠 AI

Qwen3-Coder writes less secure code when told it's for a US persona

Hirundo case study on Qwen3-Coder-30B-A3B-Instruct using the BaxBench SecretStorage task. Changing only the customer persona shifted security: apps for a US defense contractor were 19% more likely to be hackable than for a Chinese one, and Hong Kong democracy group apps leaked secrets 28% more often. Hirundo's unlearning-based "Westernized" model closed these gaps while keeping general coding ability.

evals, models, ai-safety· Added 22 Oct 2026, published 21 Oct 2026

arxiv.orgpaper🧠 AI

Symmetry-Based Parameter Efficient Low-Rank Fine-Tuning for High-Throughput Calculation of Lattice Thermal Conductivity

SBFS-FT (symmetry-based few-shot fine-tuning) adapts the MatterSim 1M universal machine-learned interatomic potential with low-rank adaptation on a small set of compounds sharing one crystal symmetry. Tested on half-Heusler (space group 216), space group 225 and spinel (227) datasets, it cut lattice thermal conductivity error 2-3 times versus the base model. It matched per-compound fine-tuning while taking 5-7 times less compute for 100 compounds.

research, training· Added 23 Oct 2026, published 21 Oct 2026

arxiv.orgpaper🛡️ Security

MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning

MPIDetector is a detection framework for multi-modal prompt injection that uses few-shot in-context learning so an LLM can reason about the semantic intent of text and image inputs, without fine-tuning. The authors built a benchmark of eight textual and seven visual attack categories plus benign sets. They report up to 90.91% accuracy on text, 99.28% on images, and up to 99.80% detection on 500 obfuscated WebInject web-agent injections, beating baselines.

AI Security· Added 24 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaper🛡️ Security

SHAKEing SLH-DSA with Non-profiled SCAs

SHAKEing SLH-DSA with Non-profiled SCAs is an eShard ePrint paper (2026/2584) on correlation power analysis of SLH-DSA-SHAKE, the NIST-standardised hash-based signature scheme. It analyses PRF inputs and selection functions, then combines subtrace averaging, partial-then-total CPA and an efficient exhaustive search to recover the full secret seed, enabling universal forgery. On a 32-bit microcontroller the attack needs about 280 to 559 signatures, and the search finishes within 45 minutes on 72 cores.

Hardware & RF· Added 24 Oct 2026, published 21 Oct 2026

github.comrepo🛡️ Security

ikow/php2shell-poc

php2shell-poc is a proof-of-concept and detection toolkit for CVE-2026-109618 and CVE-2026-109619, two PHP vulnerabilities tied to session.upload_progress handling and a Zend engine out-of-memory bailout path affecting PHP 5.4.0 through 8.5.11. The repository includes three working exploit chains, a Docker-based lab (PHP-FPM, nginx, Apache mod_php) for reproduction, and pre-built Suricata, Sigma, ModSecurity, and Lua detection rules. The author recommends disabling session.upload_progress as an interim mitigation, noting the underlying memory corruption requires a full PHP patch to fix.

AppSec, Offensive Security, Blue Team & Detection· Added 23 Oct 2026, published 21 Oct 2026

openai.comarticle🧠 AI

How we built ChatGPT’s novel ad stack for user trust and relevance

OpenAI's ChatGPT ad stack uses a custom post-trained LLM, the orchestrator, that makes tool calls for retrieval, filtering, scoring and auction nomination across stateful ad sessions. Ad selection runs in a separate service from answer generation, so ads cannot influence responses or delay them. The post covers ANN retrieval, a model-generated preamble, delivery versus impression, logging, and model-based evaluation.

agents, llm-apps, ai-infra· Published and added 21 Oct 2026

latent.spacearticle🧠 AI

[AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback

This AINews issue (20 October 2026) leads with DeepSeek's open-sourced DeepInfer, the vLLM-based inference engine behind V4.1 Flash. It covers prefill/decode separation, a 3FS-backed prefix cache with 96% hit rate, SWA Bounded Replay, and DeepSeek's claims of 155T tokens/day and $38 revenue per accelerator-hour. It also covers vLLM's within-6% decode reproduction on GB200, disputed margin estimates, and a round-up of other AI news. Only the first 40,000 of 56,439 characters were available.

inference, ai-infra, ai-policy· Published and added 21 Oct 2026

securityweek.comarticle🛡️ Security

Hijacked Developer Account Used to Plant Stealer in OVHcloud CLI

OVHcloud's official CLI was backdoored on 19 October after an attacker used a developer's hijacked GitHub account to overwrite release binaries for v0.11.0 through v0.15.0 with a secret stealer. The malicious files were live for about 94 minutes. Release immutability was not enabled, so CI/CD was bypassed. OpenSourceMalware links the account to a March 2026 compromise with a Solana-based loader and a GlassWorm wallet, but calls the same-actor link an inference.

Supply Chain, DevSecOps, Threat Intel· Published and added 21 Oct 2026

latent.spacetalk🧠 AI

AI for the Fortune 2000: How Tenex Builds an AI-Native SDLC — Alex Lieberman & CJ Hess

Latent Space interview from AI Engineer New York with Tenex cofounder Alex Lieberman and CJ Hess. Tenex has 75 people, pays engineers by story points, and reports roughly 2x engineer output over the past year. CJ describes MetaHarness, a repo-based set of skills, plans and a CLI that logs agent decisions in Git. They also cover enterprise AI adoption rates, token spend, and vertical AI. The page text is truncated.

coding-agents, ai-policy, agents· Added 23 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Active and Passive Attacks against TPM 2.0-based Full Disk Encryption

Active and Passive Attacks against TPM 2.0-based Full Disk Encryption is an ePrint paper by Freud, Hein and Klein (BSI). It shows SPI bus sniffing and interception against discrete TPMs on a mini PC and a notebook, plus a prototype UEFI firmware attack in QEMU that affects firmware TPMs. The attacks break BitLocker and all current Linux FDE implementations, including those using TPM parameter encryption.

Hardware & RF, Offensive Security· Added 24 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaper🛡️ Security

HAETAE on a Diet: Less Stack, Less Time on Low-End Microcontrollers

This ePrint paper presents an optimized HAETAE implementation, a lattice-based post-quantum signature scheme, for Cortex-M4, Cortex-M3, MSP430 and AVR. It keeps polynomials in 16 bits, shares buffers between objects with disjoint lifetimes, and replays Gaussian samples instead of regenerating them. On an ATmega2560, HAETAE-2 key generation, signing and verification run in 8,070 B of SRAM. Stack use drops up to 34% and signing is 1.18-2.51x faster than Low-Stack HAETAE.

Hardware & RF· Added 24 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Broadcast and Trace from Lattices: Collusion-Resistant and Publicly Traceable

Broadcast and Trace from Lattices is a 2026 ePrint preprint by Jeffrey Champion. It builds collusion-resistant broadcast and trace with public tracing from attribute-based encryption with succinct ciphertexts and lockable obfuscation, both known from decomposed LWE. Ciphertexts are sqrt(N)·poly(λ, log N) in size, with poly(λ, log N) keys. It is the first such scheme based on a simple, instance-independent lattice assumption.

other· Added 24 Oct 2026, published 21 Oct 2026

simonwillison.netwriteup🧠 AI

Battle Drones - a vibe coded RTS with audio-based multiplayer

Battle Drones is a browser-based Command & Conquer style RTS that Simon Willison built over 12 iterations and 321 commits, mostly with Claude Code and Claude Opus 5.5. The post gives key prompts and transcripts per version, including the "Make it a LOT more fun" run in Ultracode mode. It also covers an Agent vs. Agent mode for LLMs, audio-modem multiplayer between nearby phones, and lessons on deterministic simulation and code-generated 3D models and music.

coding-agents, agents· Published and added 20 Oct 2026

eprint.iacr.orgpaper🛡️ Security

DISCO*: DIstributed and SCalable Oblivious Joins and Oblivious Primitives

DISCO is a distributed, fully oblivious database system that combines hardware enclaves (TEEs) with oblivious primitives to hide access patterns from side-channel and leakage-abuse attacks. New distributed frameworks and communication optimizations let it run in parallel across servers. It reports 88x speedup over Jodes and 180x over SODA on non-foreign-key joins with 2^25 elements, and the first terabyte-scale results.

Hardware & RF· Added 21 Oct 2026, published 20 Oct 2026

arxiv.orgpaper🧠 AI

Beyond 4 bits: Data-Centric Post-training Quantization and Recovery

This paper studies 2-bit post-training quantization (PTQ) of six dense and mixture-of-experts models from 3.8B to 32B parameters. It finds the quantization representation matters most: vector codebooks give usable models where scalar PTQ falls to chance. Calibration and recovery data must be chosen jointly. The recipe uses about 2.3 effective bits per weight, keeps 89 to 97% of full-precision QA accuracy, and needs 1.4 to 30x less compute than the strongest QAT baseline.

research, inference· Added 22 Oct 2026, published 20 Oct 2026

en.cryptonomist.charticle🧠 AI

GPT-6 legacy programming improves as GPT-6.1 Sol scores 97.9% on COBOL test

OpenAI reports gains in GPT-6 family coding for COBOL, Fortran and Visual Basic on two evaluations. On MultiLangBench (build a SQLite-compatible database engine from scratch), GPT-6 Astra averages 87.4% across 20 languages at maximum reasoning effort, versus 37.9% for GPT-5.6 Terra. On a COBOL migration benchmark, GPT-6.1 Sol reaches 86.6% at low effort and 97.9% at higher effort, versus 5.4% for GPT-5.6 Sol.

models, evals, coding-agents· Published and added 20 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Membership Inference in Privacy-Preserving Vector Search

Membership Inference in Privacy-Preserving Vector Search is an IACR ePrint paper (2026/2570) that attacks backend-compatible protections for embedding databases using one snapshot and known plaintexts. It breaks the Scale-and-Perturb scheme of Fuchsbauer et al. (advantage 0.997 on MS-MARCO) and analyzes Rotate-and-Perturb, ideal DCRE and an encrypted HNSW index. It also tests shuffling and secret projection as mitigations.

AI Security· Added 21 Oct 2026, published 20 Oct 2026

decrypt.coarticle🧠 AI

Mastercard Opens Up AI Agent Payments With Early Access and Live Demo

Mastercard's Agent Pay for Machines is a system, opened to early access in October 2026, that lets AI agents discover paid services, agree to terms and pay within human-set limits. It builds on the x402 protocol: an agent that gets a "402 Payment Required" response signs a payment voucher the provider verifies. A live demo made nine payments to two merchants, settled through Coinbase, Base and BVNK. Mastercard is releasing buyer and seller APIs, a toolkit and a sandbox.

agents· Published and added 20 Oct 2026

theblock.coarticle🧠 AI

Mastercard opens early access to AI agent payments following pilots with Coinbase, Base and Cloudflare

Mastercard Agent Pay for Machines is a set of buyer- and seller-side APIs, a toolkit and a sandbox, opened to early-access developers in October 2026. Pilots involved Cloudflare, Ant International, BVNK, AIsa, Base and Coinbase. In a Cloudflare Connect demo, an AI agent made nine payments over x402, settled onchain on Base, with BVNK as agent wallet. It is not yet commercially available.

agents· Published and added 20 Oct 2026

arxiv.orgpaper🛡️ Security

After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

CarryoverBench is a benchmark of 12 personal-assistant scenarios and 101 attack tasks for carryover attacks, where a one-time indirect prompt injection planted in agent memory files or scheduled tasks re-fires in later sessions. Three trigger channels (Instant, Autonomous, Latent) are scored by a rule-based verifier with separate planting and triggering stages. Across five frontier models, payloads re-fire over five rounds without measurable decay. Porting the Latent channel to the Hermes runtime weakens the effect but does not remove it.

AI Security· Added 22 Oct 2026, published 20 Oct 2026

arxiv.orgpaper🧠 AI

Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V

Code2Video-Compass is a benchmark of 2,104 tasks for code-based video generation, where multimodal LLMs write executable programs that produce complete videos from text (T2V), image (I2V) or video (V2V) inputs. Tasks span 10 categories and 24 subtypes. Scoring uses 12 objective metrics and five MLLM-judge metrics. Across 15 proprietary and open-weight models from nine families, performance falls as construction, dynamic animation and state-dependency complexity rise.

evals, multimodal, research· Added 22 Oct 2026, published 20 Oct 2026

arxiv.orgpaper🧠 AI

A Multimodal Engineering GraphRAG Framework for Post-Wind-Event Building Assessment and Recovery Inference

This paper presents a multimodal engineering GraphRAG framework that links post-wind-event damage evidence from images and reconnaissance reports to building-condition states, recovery actions and downtime. Evidence is stored as a provenance-preserving, component-level representation, and graph-aligned retrieval uses compatibility, contradiction, evidence-precedence and abstention checks. Demonstrated on tornado-affected low-rise homes, it beats BaselineRAG and Structured Baseline RAG, and ablations test each component.

research, llm-apps, multimodal· Added 22 Oct 2026, published 20 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Regular Syndrome Decoding Is Easier Than Previously Estimated

Preprint by Jiseung Kim, Minkyu Kim, Changmin Lee and Hochang Lee on the Regular Syndrome Decoding (RSD) problem. It presents a hybrid-algebraic attack that balances zero-coordinate guesses and syndrome-based eliminations across regular blocks. Parameter sets in Ferret, Wolverine and committed VOLE fall below 128-bit targets by up to 67 bits, and the revised Liu et al. (EUROCRYPT 2024) PCG sets cost under 2^111 field operations.

other· Added 21 Oct 2026, published 20 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Regular Syndrome Decoding Is Easier Than Previously Estimated

Preprint 2026/2563 presents a refined hybrid-algebraic attack on Regular Syndrome Decoding (RSD) that balances zero-coordinate guesses and syndrome-based eliminations across all regular blocks. It puts at least one parameter set each from Ferret (CCS 2020), Wolverine (IEEE S&P 2021) and committed VOLE (CCS 2025) below the 128-bit target, with losses up to 67 bits. PCG attack costs improve by up to 29.77 bits (non-binary) and 25.91 bits (binary), and the revised Liu et al. (EUROCRYPT 2024) 128-bit sets fall below 2^111 field operations.

other· Added 21 Oct 2026, published 20 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Graphs and cycles in curve-based collision walks

Graphs and cycles in curve-based collision walks is an IACR ePrint paper (2026/2560) on van Oorschot-Wiener style collision attacks in the multi-user setting. It covers elliptic curve discrete logarithms and isogeny pathfinding on supersingular F_p^2 and F_p curves, and proposes new pseudorandom walks. For F_p^2 curves, L keys need about L + log(L) useful collisions with no infiltrator. For F_p curves, about 0.75L keys fall to L collisions with an infiltrator.

other· Added 21 Oct 2026, published 20 Oct 2026

x.comtool🧠 AI

G (@gg_guy03) on X

WhatThePort for Linux is a Rust utility that lists the dev servers still running in the background, the project that started each one, and its RAM use. It links each server to the Claude Code or Codex session that launched it, and stops the whole process tree without touching databases. The CLI offers `wtp`, `wtp stop <port>` and `wtp --json`. A reviewer notes the Codex resolver keeps the newest transcript per working directory, so session matches can be wrong.

coding-agents· Added 20 Oct 2026, published 19 Oct 2026

x.comthread🛡️ Security

Nick Frichette (@Frichette_n) on X

Datadog Security Labs announcement, posted by Nick Frichette, of research on steering the evaluations of a prompt-injection detector called "Jev". The team's method cut its detection rate from about 83% to about 4% in their tests. They also used it to bypass LangChain's experimental tool-risk gating feature that is based on Jev. The tweet gives no method details and links to the full article.

AI Security· Added 21 Oct 2026, published 19 Oct 2026

securityweek.comarticle🛡️ Security

Siemens Software Center Vulnerability Exploited in ClickFix Malware Attacks

CVE-2026-110936 is a DLL search-path flaw in Siemens Software Center (CVSS v4 8.4), fixed in version 4.0.9.8. Attackers paired a validly signed copy of the program (3.5.8.7) with their own DLLs for side-loading, delivered through the Romulus ClickFix platform. Siemens says its channels were not breached and advises behavior-based detection over file hashes. Huntress reported the flaw.

Threat Intel, Blue Team & Detection· Published and added 19 Oct 2026

arxiv.orgpaper🧠 AI

Can It Actually Work? Synthesizing Functional CAD Mechanisms

FunCAD-Harness is a framework in which LLM agents design CAD mechanisms and revise them using physical simulation feedback. It turns abstract functional requirements into candidate-specific physical tests. The paper also introduces FunCADBench, a benchmark of 46 mechanism families with interdependent, multi-step operations. Experiments on frontier LLM agents show it exposes mechanical failures that visual inspection misses and raises functional success over standard simulation-augmented baselines.

research, evals, agents· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

OpenVLHarness is a multimodal reasoning harness for MLLMs built on a capability layer (task-level tool interfaces plus evidence rendering) and persistent multimodal memory that stores images, structured data and web references as addressable artifacts. A coding interface runs generated programs over stored data. Across 22 benchmarks and eight backbones it adds 9.7-12.6 points over no-tool baselines, and GPT-6 Luna at medium effort beats Codex and Visual Sketchpad at maximum effort using at most 37% of their tokens.

agents, multimodal, research· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

MemT-1.0: Towards Memory-Native Evolution

MemT-1.0 is a memory foundation model architecture that builds memory into model computation. It builds on Metis, uses Gated DeltaNet-2 for token-level memory updates within each turn, and adds Mixture-of-Storage to scale capacity. Training used 34B tokens in continued pre-training and post-training. MemT-1.0-Nano and MemT-1.0-Flash beat parametric memory baselines and stay competitive with retrieval methods. At 128K history, Nano gives about 1.86x inference speedup and 66x less persistent storage than a full-context KV cache.

research, models, agents· Added 21 Oct 2026, published 19 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Registered ABE via Predicate Encodings, Revisited

Registered ABE via Predicate Encodings, Revisited is an ePrint paper by Junichi Tomida (October 2026) that gives a new definition of predicate encodings suited to registered attribute-based encryption. It yields the first Reg-ABE schemes for (non-)zero inner product and for conjunctions/disjunctions with O(log L)-size ciphertexts. It also gives a registered broadcast encryption scheme with O(log L)-size ciphertexts under the standard k-Lin assumption, not the generic group model.

other· Added 20 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation

Mise-en-Video (MeV) is a multi-shot video generation framework where creators stage shots in 3D space and then generate the matching video. It combines hierarchical attention for multi-level narrative consistency with 3D-aware layout guidance for per-shot spatial control. The authors built a 160K-video dataset with hierarchical multi-shot texts and oriented 3D bounding boxes, and report gains over baselines in quality, consistency and subject controllability.

research, multimodal· Added 21 Oct 2026, published 19 Oct 2026

eprint.iacr.orgpaper🧠 AI

Analysis of an AI based code distinguisher

The paper analyses DeepDistinguisher, a transformer-like model that tells Goppa codes apart from random linear codes. Saliency maps and attention visualisation reveal a low-weight-row artifact in the random training instances that the model partly relies on. A pairwise-XOR rule inspired by minimum distance correlates strongly with the model's predictions, and the model loses most of its power on random matrices meeting both constraints. This suggests it exploits general combinatorial properties, not hidden algebraic structure.

research· Added 20 Oct 2026, published 19 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Analysis of an AI based code distinguisher

Analysis of DeepDistinguisher, a transformer model that tells Goppa codes from random linear codes. Using saliency maps and attention visualization, the authors find a low-weight-row artifact in the random training instances that the model partly uses. They propose a pairwise-XOR rule on generator matrix rows that correlates strongly with the model's predictions. On random matrices meeting the minimum distance and XOR constraints, the model loses most of its accuracy, so it exploits general combinatorial properties rather than hidden algebraic structure.

AI Security, other· Added 20 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

EpiLens: Lightweight RAG for Epidemiological Knowledge Acquisition

EpiLens is a lightweight, open-source retrieval-augmented generation package that applies a fixed retrieval template and output schema to every paper in a corpus and links outputs to source passages. On a corpus of 2,297 epidemiology papers, its classifier matches or exceeds supervised and zero-shot baselines on four tasks without task-specific training data, scored against 214 manual labels. It also compares model-based study shares across parameters and pathogens.

llm-apps, research· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

Assisted Turbulence Modeling via Data Assimilation and Machine Learning for Turbomachinery Flows

This paper presents a hybrid framework for axial compressor flow that couples a Multi-Fidelity Ensemble Kalman Filter (MFEnKF) with machine learning. The filter merges PIV experiments with steady RANS and unsteady hybrid RANS/LES simulations. A neural network trained on the enriched data predicts Navier-Stokes volume forcing terms from velocity, velocity gradients and turbulent viscosity. A Mixture of Experts fixes local errors near blade tips, giving lower experimental discrepancy than baseline RANS.

research· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

E-Layout: Layout-Stage Logic Restructuring via RL-Optimized Equality-Saturated Graph Retrieval-Augmented Generation

E-Layout is an ML-driven framework for post-placement logic restructuring in IC physical design. It builds equivalent logic alternatives with e-graph equality saturation, links logic choice to physical realization through a graph-based RAG model, and refines the choices with reinforcement learning on design-level timing feedback. On 9 designs it gives about 6% TNS and 2% WNS improvement and 1% less area than a commercial physical design flow.

research· Added 21 Oct 2026, published 19 Oct 2026

openai.comarticle🧠 AI

Advancing Coding in Low-Resource Programming Languages

OpenAI describes two evaluations for coding in low-resource languages such as COBOL, Fortran and Visual Basic. MultiLangBench has a model build a SQLite-compatible database engine in 20 languages. The COBOL migration eval requires byte-for-byte output parity. GPT-6 Astra scores 87.4% on MultiLangBench (GPT-5.6 Sol: 26.8%), and GPT-6.1 Sol reaches 86.6% on COBOL migration at low effort. The setup is on GitHub.

evals, coding-agents, models· Published and added 19 Oct 2026

x.comadvisory🛡️ Security

lee1981 (@lee1981b) on X

CVE-2026-106931 is an OS command injection (CWE-78) in the statistics processing of EG Secure Solutions SiteGuard Server Edition, a host-based WAF. It can give root or SYSTEM command execution. The vendor and JVN confirm exploitation on 14 October 2026. The post lists fixed builds (Ver8.00 Update 5, Ver7.00 Update 6 on FreeBSD), the IIS exclusion, the workaround of disabling statistics, and a SOC trail starting with diagnostic preservation before patching.

Blue Team & Detection, AppSec· Added 21 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🛡️ Security

RAGLeak: Supply-Chain Privacy Backdoors in Retrieval-Augmented Generation

RAGLeak is a supply-chain privacy backdoor attack on retrieval-augmented generation. When triggered, the backdoored generator reversibly obfuscates retrieved private documents, and an auxiliary LLM recovers them. Tested on three model families and three domains, it reaches up to 100% attack success rate, loses at most 10 points under detection-based defenses, and survives clean fine-tuning and changes of model scale and version. Source code is released.

AI Security, Supply Chain· Added 21 Oct 2026, published 19 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Efficient and Compact High-order Masking Raccoon on Memory Constrained Devices

The paper presents the first efficient, compact implementation of high-order masked Raccoon (lattice-based signature, CRYPTO 2024) on ARM Cortex-M4, up to 32 masking orders. It uses 3+3+3 layer-merged 32-bit NTT/INTT with lazy reduction, a negative double Montgomery reduction, and one-shot SHAKE256 sampling (at least 1.80x faster). It beats the reference by 1.85x-2.25x and masked Dilithium3 at orders 2, 4 and 8. Second-order leakage tests show DPA resistance once micro-architectural transitional leakage is mitigated.

Hardware & RF· Added 20 Oct 2026, published 19 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Optimizing HQC with Enhanced Parallel Binary Polynomial Multiplication on GPUs

This paper presents an end-to-end GPU implementation of the HQC code-based key encapsulation mechanism. It speeds up GF(2) polynomial multiplication with a parallel Frobenius additive FFT and a Toeplitz matrix-vector mapping onto INT1 tensor cores. On an RTX 4090 the multiplier reaches 3,828k polymul/s, about 2.9x the earlier HIGH implementation. Full KEM throughput is 1.56x, 1.55x and 2.03x higher for keygen, encaps and decaps. Five thread-to-KEM mapping variants are tested on RTX 3090 and Jetson AGX Orin.

other· Added 20 Oct 2026, published 19 Oct 2026

arxiv.orgpaper🧠 AI

Hybrid Reasoning Agents: LLM agents that think in latent space, act through text

Hybrid Reasoning Agents (HybridAgents) are LLM agents that switch between latent reasoning and text-based interaction in one generation process. A lightweight HybridLink handles mode transitions, continuous working memory keeps hybrid context across turns, and HybridSFT plus HybridRL train when to think latently and when to act in text. Across 3 model scales and 11 benchmarks, the paper reports 10.4% higher performance, 35.5%-54.7% fewer tokens, and 1.8x-2.6x faster inference.

research, agents, training· Added 19 Oct 2026, published 18 Oct 2026

x.comtool🧠 AI

Dan Kornas (@DanKornas) on X

Coral is an open-source (Apache 2.0) agentic IDE that runs Claude Code, Codex, Gemini CLI and Pi.dev together as one coordinated team on a shared codebase. It puts sessions, tasks, messages and controls behind a shared board and browser dashboard. Features include a task queue with dependencies and review holds, an agent message board, git-worktree sessions tracked against main, and live terminal access from a browser or phone.

coding-agents, agents· Added 19 Oct 2026, published 18 Oct 2026

tomshardware.comarticle🧠 AI

Anthropic's proposed AI safety bill only kicks in if 50 deaths or $1B in damages

Tom's Hardware reports, citing Politico, that Anthropic is lobbying for a federal AI safety bill based on its Advanced AI Framework. The Commerce Department could seek to block a model release only if it risks $1 billion in damages or more than 50 deaths or injuries. Registered third-party evaluators would report risks within 72 hours, and a D.C. federal judge would decide. Commenters call it regulatory capture.

ai-policy, ai-safety· Added 19 Oct 2026, published 18 Oct 2026

eprint.iacr.orgpaper🛡️ Security

How Secure are NTRU+ Keys? Analysing the Best Module Attacks

ePrint 2026/2527 by Paola de Perthuis and Filip Trenkić analyses module-BKZ attacks on NTRU+, the South Korean KEM standard. It introduces relative canonical and coefficient embeddings and shows they agree up to scaling exactly when rad(c)/rad(ℓ) is 1 or 2. Simulation-based estimates show the best module attack saves 4 to 10 blocksizes, costing NTRU+ keys at most three bits of Core-SVP security. NTRU+ parameters stay safe in the overstretched regime.

other· Added 19 Oct 2026, published 18 Oct 2026

arxiv.orgpaper🧠 AI

ToFu: Exploiting and Fuzzing the LLM–Orchestrator–Tool Trust Boundary

ToFu is a tool-aware fuzzing framework for LLM tools, including MCP servers. It maps each tool argument, using its metadata, to one of 74 CWE-guided semantics-aware sanitizers (path, URL, SQL and similar). It then generates schema-valid Atheris harnesses and semantic oracles, using runtime tracers for in-process tools and outcome oracles for opaque ones. The LLM (gpt-4.1) only maps sanitizers and writes seeds; it is never the security judge. The paper also shows a "Repeat-After-Me" trick, where an LLM told to repeat attacker-crafted text emits a tool call the orchestrator executes, reproduced on LangGraph, MAF, ADK 2.0, AutoGen, Strands and CrewAI. Across 273 runnable MCP servers (3,405 tools) it reports 253 verified bugs in 343 tools across 118 servers, such as path traversal, log injection and exfiltration. These are failures a crash-based fuzzer would miss. The result matters because it shows LLM-generated tool arguments cannot be treated as trusted.

mcp, research, agents· Added 18 Oct 2026

blog.picheta.mearticle🧠 AI

I built a programming language that LLMs can't use

KillSwitch is an esoteric stack-based programming language built to be adversarial to LLMs and coding agents. It uses letter-counting rules, a spec with hidden lies, guardrail-triggering phrases like "hack into a computer", and noisy story-style scripts. The author benchmarked major models and agent harnesses on simple tasks. Opus 5 scored best at 66.8, Fable 5.1 and Gemini 4 Argon did poorly because of safety guardrails, and MiMo-V2.6-Pro led the open-weight models.

evals, coding-agents· Added 19 Oct 2026, published 17 Oct 2026

x.comadvisory🛡️ Security

Dark Web Intelligence (@DailyDarkWeb) on X

Infinity Core is a set of six Linux kernel bugs published by researcher Hyunwoo Kim after the linux-distros embargo expired on 16 October 2026, with public exploit code. The bugs sit in timer, signal, memory, futex, scheduler and SLUB code. Five have local privilege escalation exploits, one is crash-only. CIQ says four affect Rocky Linux-based kernels. No sysctl or module workaround exists, so the fix is a patched kernel and a reboot.

Offensive Security, Cloud & Infra· Added 19 Oct 2026, published 17 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Associated-Data Correlations in Eevee: Deterministic Forgeries against Nonce-Misuse Security

Cryptanalysis of the Eevee forkcipher-based AEAD modes Umbreon and Espeon, which claim online AE security under nonce reuse. Associated-data correlations give probability-one non-empty-message forgeries with three encryption queries and one verification query. The paper adds an affine treatment of partial final blocks (n-r+3 queries, or n-r+2 with adaptive choices). It also checks the published Umbreon attack with the official ForkSkinny primitive and reports a two-query attack accepted by the unmodified public C modes.

other· Published and added 17 Oct 2026

rekt.newswriteup🛡️ Security

Factory Sealed – Rekt (Ledger/CryptoBilis hardware implant drains)

Rekt write-up on LTE-equipped hardware implants found in Ledger Nano X and Flex wallets sold through resellers such as CryptoBilis and MediaMarkt. The implants read the recovery phrase off the screen during setup and exfiltrate it over an eSIM/LTE modem, so Ledger's Genuine Check and Secure Element never detect them. It covers the teardown timeline (Joe Grand, Mark Karpelès, a Japan-based researcher), the 47-minute multi-chain drain (Bitquery estimates about $102M across 324 wallets, unverified by Ledger), the laundering path via USDD, THORChain, Tornado Cash and Zcash, the CryptoBilis ownership change, and the failure of "authorized reseller" trust.

Blockchain, Hardware & RF, Threat Intel· Added 17 Oct 2026

thingstodoapi.comtool🧠 AI

Show HN: Things to Do API

Things to Do API is a hosted knowledge base of local events (shows, talks, pop-ups, markets, festivals) that you query in natural language, for example `/v1/search?q=comedy+in+san+francisco+this+weekend`. It returns structured JSON with title, category, local start time, venue and ticket and source links. It also exposes an HTTP MCP endpoint, added with `claude mcp add --transport http thingstodo https://api.thingstodoapi.com/mcp`, so agents can use it as a tool. Coverage is live for the San Francisco Bay Area, with New York City and Los Angeles coming. Pricing is pay-as-you-go from $5 per 1,000 calls, the first 1,000 a month are free, and there is a 300 calls/min limit.

mcp, llm-apps· Added 18 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🛡️ Security

RATION: Towards Quantitative Risk-Based Access Control for AI Agents

RATION is a security framework for AI agents that tracks measurable risks from agent actions and enforces quantitative constraints during task execution, instead of simply restricting actions. It builds a task-specific policy from explicit constraints in the user request plus implicit risks calibrated from historical runs of similar tasks. Experiments on four security benchmarks show strong security with high task utility across models and environments.

AI Security· Added 21 Oct 2026, published 16 Oct 2026

claude.devarticle🧠 AI

How the Claude Code team does code review

The Claude Code team describes how it reviews code when Claude writes about 90% of it. Layers include pre-PR self-verification and fresh-context subagent review, an automated Claude review on every PR, and agents that vote on each finding. Risk-tier classifiers, trusted-author rules, merge queues, feature flags and on-call back these up. From June to September, merged PRs more than doubled while reverts fell over 40%. It also covers how they measure reviewer noise, treat incidents as evals, keep review loops converging (one PR went through 50+ rounds overnight), and spread codebase knowledge through Claude-generated explainers.

coding-agents, ai-policy· Added 17 Oct 2026, published 16 Oct 2026

anthropic.comwriteup🛡️ Security

Claude reveals ECDSA curve origins

Anthropic's Frontier Red Team reports that Claude recovered how the NIST P-192/224/256/384/521 and ANSI X9.62 curve seeds were generated. They are outputs of the C library's lrand48 LCG seeded with 1997–98 Unix timestamps, not hashes of a passphrase. The method scanned for weak-PRNG signatures, then used LLL lattice reduction to recover the truncated LCG state and stepped it back to srand48 initialization. Claude also traced some base points to the FreeLIP/NTL random generator. Reproducible Python is included. The authors say this is not an attack and makes deliberate backdoors less plausible. The B-163 seed and the base points of P-224/256/384/521 and the binary curves remain unexplained.

other· Added 17 Oct 2026, published 16 Oct 2026

anthropic.comwriteup🧠 AI

Claude reveals ECDSA curve origins

Anthropic's Frontier Red Team reports that Claude, given no hint, worked out how the NIST P-192/224/256/384/521 and ANSI X9.62 curve seeds were generated. They came from the C library's lrand48 LCG seeded with Unix timestamps from 1997–98, not from a hash of a phrase. Claude found this by scanning for weak-PRNG signatures and recovering the PRNG state with LLL lattice reduction. It also traced several prime-curve base points to the FreeLIP random generator. The post includes Python code that reproduces the seeds and base points. It says this is not an attack and makes backdoor claims less plausible. B-163 and the other base points remain unexplained.

research· Added 17 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery

SEER-Repro is a benchmark of 20 published papers based on the SEER cancer registry, with the data needed to reproduce their findings. An LLM agent reproduces 77.4% of 2,190 atomic claims. A second agentic pipeline finds alternative analytical choices and reruns the analyses, flagging potentially consequential choices in 9.5% of fully reproduced findings for expert review.

research, evals, agents· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper

FuTransformer is a CUDA implementation of a Llama-style Transformer block for NVIDIA Hopper GPUs. It uses FP8 prefill with fused GEMM epilogues and INT4 weights plus an INT4 KV-cache copy for decode, with a block-diagonal Hadamard transform to cut cache quantization error. On one H100, prefill is up to 1.48x faster than compiled PyTorch FP8, and INT4 decode is 1.3-2.4x faster than the faster PyTorch baseline. Llama-3.1-8B decode takes 2.8 ms per step at batch one, versus 8.1 ms for compiled transformers. WikiText-2 perplexity rises from 6.24 to 7.23 with round-to-nearest INT4 weights, or 6.99 with GPTQ.

inference, research· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search

GLOBE is an agentic framework that optimizes e-commerce product listings for generative search by storing strategies in an evolving handbook of explicit, field-scoped behaviors. An Editor applies behaviors and gets rank-based feedback, a Reflector turns it into updates, a Moderator removes redundant proposals, and a Curator commits changes. Harmful behaviors are deactivated. Structured behaviors beat monolithic prompt optimization and transfer to unseen product categories.

agents, research· Added 20 Oct 2026, published 16 Oct 2026

a16zcrypto.comarticle🛡️ Security

Fast post-quantum signature aggregation with lattice SNARKs

a16z crypto announces Aerie, a lattice-SNARK system that aggregates Falcon-512/1024 signatures into one ~66 KiB proof. On an M4 Max laptop it handles 32,768 signatures in 0.65 s (~50k/s), verifies in 54 ms, and costs ~42 bytes per signature. It benchmarks against Orthus and Ethereum's leanVM hash-based XMSS aggregation, and argues that recursion-free lattice aggregation is simpler than hash-only designs. It also covers Falcon's hardware-wallet and side-channel constraints and why private payments need lattice encryption such as ML-KEM.

other· Published and added 16 Oct 2026

a16zfrontier.comarticle🛡️ Security

Fast post-quantum signature aggregation with lattice SNARKs

Aerie is an a16z crypto and LayerZero Labs system that aggregates Falcon-512 and Falcon-1024 lattice signatures into one lattice SNARK. On an Apple M4 Max it aggregates 32,768 Falcon-512 signatures in 0.65 seconds, with 54 ms verification and about 42 bytes per signature. The post compares it with Ethereum's hash-based leanVM and XMSS plan and Orthus, and covers Falcon signing limits on hardware wallets.

other· Added 22 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

FedRAPP: Federated Test-Time Prompt Tuning for Vision-Language Models with Reliability-Aware Prompt Personalization

FedRAPP is a personalized aggregation framework for Source-Free Federated Test-Time Prompt Tuning (SF-FTTPT), where clients adapt CLIP soft prompts on unlabeled, non-IID test streams without source data. It combines reliability-aware client assessment, a server-side exponential moving-average prompt memory and similarity-guided peer aggregation. Across nine CLIP benchmark datasets and ImageNet variants it beats standard federated aggregation baselines while keeping prompt-only efficiency.

research, multimodal· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation

HardEval is an execution-verified benchmark for language-model security hardening, built from Red Hat Enterprise Linux 8 STIG controls that fail on an unhardened baseline. Models receive only the required security outcome and write a Bash script, which runs on a live VM and is graded fail to pass with OpenSCAP/OVAL checks. Fourteen frontier and open-weight configurations show uneven results across domains, with plausible code that misses the exact compliance condition. The benchmark is public.

evals, research· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🛡️ Security

HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation

HardEval is an execution-verified benchmark for LLM-driven security hardening, built from Red Hat Enterprise Linux 8 STIG controls that fail on an unhardened baseline. Models receive only the security outcome and write a Bash script, which runs on a live VM and is graded fail-to-pass by OpenSCAP/OVAL checks. Fourteen frontier and open-weight configurations show uneven results across SSH, authentication, audit and kernel domains, with a common failure of plausible code that misses the exact compliance condition.

AI Security, Cloud & Infra, GRC· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management

This paper proposes a framework for auditing LLM-agent-generated stakeholder preferences before they are used as weights in multi-objective optimization for healthcare operations. Experiments on outpatient appointment scheduling and emergency department configurations show that explicit ratings vary by role and clinic conditions, deliberation can erase role differences, and pairwise choices depend largely on option order. Robust weighted-sum models often select different schedules than average weights.

research, agents, evals· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible Granularity

FlexPart is a framework for text-controlled 3D mesh segmentation that assigns discrete part IDs to mesh faces through a view-independent part-identity field. It uses a control prompt of part names with location and shape clauses, trained on a VLM-built multi-granularity dataset. On FlexPartBench it raises average mIoU by 22% over the strongest baseline, and by 15% with planner-completed prompts.

research, multimodal· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

A Language-Informed Loss for Visual Generation

LILIE (Language-Informed and Lossless Image Encoder) is an invertible image transform built from a normalizing flow transformer, trained jointly with a vision-language model via next token prediction so captions can be recovered from noised features. The encoder supplies a language-informed loss for text-to-image generation. JiT models trained with it cut gFD from 66.84 to 53.01 against a pixel-only baseline on the GPIC dataset. Code, encoders and models are released.

research, multimodal· Added 20 Oct 2026, published 16 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Analysis of the Multi-Key Optimization for SPECK

The paper revisits the multi-key optimization for SPECK, a code-based signature scheme that uses the Permutation Code Equivalence Problem (PEP) as a trapdoor for the Permuted Kernel Problem (PKP). Each SPECK round has soundness error 1/2, which inflates signatures, and the SPECK authors had warned that naively using multiple public keys creates security concerns. The authors analyse those concerns, give conditions and parameter constraints under which multiple keys can be integrated securely, and show that conservative parameters perform poorly but leave room for improvement. They also build a ring signature scheme on the same construction.

other· Added 17 Oct 2026, published 16 Oct 2026

x.comthread🛡️ Security

Nicholas Martin (@ndgmlondon) on X

An X post advises auditing every MCP write tool against the database role it actually runs under. A shared service key lets prompt injection trigger unapproved writes, so each agent session should get a read-only role, with a test that writes are denied. Replies note that MCP servers often inherit ambient host credentials or can escalate through a second connection pool, and suggest also testing that another tenant's rows are unreadable with the same role.

AI Security, Identity & Access· Added 18 Oct 2026, published 16 Oct 2026

eprint.iacr.orgpaper🛡️ Security

SLEEK: Sparse Quasi-Cyclic Codes with Closed-Form DFR Key Encapsulation

Introduces SLEEK, a QC-MDPC code-based KEM using a three-iteration parallel bit-flipping decoder and a closed-form decoding-failure-rate (DFR) estimate, enabling parameters with analytically bounded failure probability and standard IND-CCA transforms. SLEEK-LT targets IND-CCA for long-term keys; SLEEK-E targets IND-CPA for ephemeral keys using a new QC key structure with security equivalent to QC-MDPC and cheaper key generation. Parameter sets cover 80/128/192/256-bit security, and the optimized AVX2 implementation gives ciphertexts 4.9x smaller than HQC (47% slower) and 1.3x–2.7x faster than BIKE.

other· Added 17 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

Enhancing RAG-based Medical VQA with Gated Multimodal Representations

This paper presents a multimodal retrieval-augmented generation framework for Medical Visual Question Answering. A Gated Multimodal Unit learns a joint query representation from the medical image and the clinical question, so evidence retrieval uses both modalities while the Med-LVLM stays frozen. On benchmark datasets it consistently beats a reference Med-LVLM and stays competitive with state-of-the-art methods. The page gives no dataset names or numbers.

research, llm-apps, multimodal· Added 20 Oct 2026, published 16 Oct 2026

eprint.iacr.orgpaper🛡️ Security

I Want to Ride My BIKE: Customizing Bit-Flipping Decoders for Ephemeral Key KEMs

ePrint paper presenting the first optimized implementation of the BF-max bit-flipping decoder for the code-based KEM BIKE, combined with other decoders to trade off decoding failure rate, runtime, public-key and ciphertext size in ephemeral-key settings. It cuts public-key and ciphertext sizes by 7.8% versus LeanBIKE at similar speed and DFR, and gives a combined size 22% below BIKE and 2.79x below HQC. It shows BIKE can fit constrained protocols such as IKEv2, which matters for practical post-quantum migration.

other· Added 17 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🛡️ Security

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection

MobileInject is a benchmark for testing MLLM-based smartphone agents against indirect multimodal injection. It has an interactive evaluation framework with 11 scenarios, 9 security-risk categories and 108 executable risk instances. It adds Cross-Modal Consistency Injection, Multi-Role Collaborative Deception, Reasoning-Camouflage Injection and a Reasoning Security Diagnosis Framework. Experiments find broad vulnerability, with many failures from early reasoning hijacking.

AI Security· Added 20 Oct 2026, published 16 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Power Analysis on SQIsign via Ideal Reconstruction from Quaternion Leakages

ePrint paper identifying five side-channel vulnerabilities in the signing procedure of Round-3 SQIsign, the isogeny-based signature scheme in NIST's additional post-quantum signature process. It gives polynomial-time algebraic algorithms that recover the secret key from leaked quaternion/ideal intermediate values, including cases where only partial bits leak. It also demonstrates power analysis on the SQIsign source code to extract the needed leakage, which earlier work on Round-1 or toy parameters did not do.

Hardware & RF· Added 17 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

PrairieFire: Igniting High-Throughput Updates in Large-Scale Approximate Nearest Neighbor Search

PrairieFire is an SSD-based approximate nearest neighbor search system for billion-scale vectors, built for high update throughput. It uses buffered updates and batched local rebuilds, with cascaded adjustments, concurrency control and CPU-GPU-SSD cooperation. Against state-of-the-art systems it reports about 3-35x update throughput, 3-5x search throughput and 1.5-8.7x cost efficiency. It has run in RedNote production for two months.

research, llm-apps· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaper🧠 AI

MUB: An Identity-Masked Benchmark for Music Understanding in Multimodal Language Models

MUB (Music Understanding Benchmark) is a set of 500 identity-masked recordings with existing annotations for tempo, key, time signature and structural intervals. It covers all 24 keys, tempos of 47 to 180 BPM and 4,676 intervals, and strips titles, artists and platform IDs from inputs. Baselines reach 53.6% tempo accuracy (DSP) and 98.4% time-signature accuracy (constant 4/4). No multimodal LLM has been tested yet, and rights clearance is unresolved.

evals, multimodal, research· Added 20 Oct 2026, published 16 Oct 2026

latent.spacearticle🧠 AI

[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment

The 10/14–10/15/2026 AINews issue. Its lead story is Goodfire's Nick Cammarata essay "Neural Networks Are Already Clean", which argues agentic analysis resolves many known cases of polysemanticity and superposition. Neel Nanda, Leo Gao and Jake Mendel push back. It also covers Meta's Muse Spark Open (816B total / 42B active MoE, 1M context, custom license, Artificial Analysis index 39, vLLM day-0 support and quantizations), Nemotron 3.5, MAI-Base-2 and Gemini 4 Argon evals. Further items cover Vals' refund-agent and MiMo task-leakage findings, TPUv7 and Vera Rubin inference benchmarks, Perplexity's SPACE sandbox, RL training systems (TRL tree packing, bitwise-consistent vLLM RL) and Sakana's Agentic Scientist.

ai-safety, models, research· Published and added 16 Oct 2026

endorlabs.comarticle🛡️ Security

Why Your SCA is Always Wrong | Endor Labs

Explains why traditional SCA tools are inaccurate: they parse package-manager manifests and assume those match what the code actually uses. It walks through phantom dependencies, misused dependency scopes, direct use of transitive dependencies and unused dependencies, using Python and JavaScript as examples. It argues for SCA based on program analysis, with source code as ground truth cross-checked against manifests and the file system. Useful for evaluating SCA tools and understanding SBOM accuracy limits.

Supply Chain, AppSec· Published and added 16 Oct 2026

huggingface.coarticle🧠 AI

Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline

Announces Nemotron-pretraining-Indic-v1, about 2.8T tokens across 22 Indian languages (2,601B native-script, 224.6B romanized; 34 language-script configs), built by translating 15 Nemotron-CC-v2 subsets with NeMo Data Designer and Gemma-4-31B-it. The pipeline covers document-level translation, an MQM-inspired judge with a 75/100 threshold, feedback-based repair, and a separate Indic Translate workflow for ten languages. Continued pretraining of Nemotron 3.5 Super VL with 10B Indic tokens raised all five Indic benchmarks by 4.98–9.82 points. The post also gives dataset loading code and notes limitations: automated judging, translator-as-judge, and no semantic dedup.

training, models, evals· Published and added 16 Oct 2026

github.comrepo🧠 AI

OpenMOSS/MOSS-Image

MOSS-Image is an open-source text-to-image model family from OpenMOSS with a 5B backbone, released October 2026 as MOSS-Image-Base and MOSS-Image-SFT. It supports JSON layout control with bounding boxes, text rendering inside images, and prompts up to 4K tokens. The repo gives a Diffusers pipeline, a Gradio app, a ComfyUI plugin, LoRA training guidance, a prompt-enhancer skill and day-0 SGLang and vLLM-Omni support.

models, multimodal, inference· Added 20 Oct 2026, published 16 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Shorter Hash-Based Signatures via Guarded Sharing in a DAG Model

Proposes "guarded sharing", a technique that moves few-time signatures in SPHINCS-style stateless hash-based schemes from a tree model to a DAG model. Combined with bucket thinning, hash chains and rejection sampling, it yields BGS-CC, which improves on the prior best few-time scheme BPORS-C+BFP. For 128-bit security and a use quota of Q=2^24 it gives 2,228-byte signatures, the first SPHINCS-based stateless signature shorter than ML-DSA-44's 2,420 bytes. This matters for PQ migration because signature size is the main drawback of SLH-DSA.

other· Added 17 Oct 2026, published 16 Oct 2026

huggingface.coarticle🧠 AI

Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint

IBM announces Granite-Switch-4.1-8B and -30B. Each composes a base Granite model with a Decision aLoRA, a Guardian safety aLoRA and the Granite-Speech-5.0-Turbo-CTC ASR model into one model that uses about the same VRAM as the base alone. Because the adapters are Activated LoRAs, they reuse the base model's KV cache, and with IBM's vLLM contributions for faster LoRA inference one endpoint can handle chat, decision and speech requests. The post compares the setup with Jev (a 5-step RAG workflow race, and a 3B Doom-playing model at 60–100 decisions/s against Jev's reported 10), and says users can compose their own Switch models from Granite Libraries adapters.

models, inference, multimodal· Published and added 15 Oct 2026

x.comthread🛡️ Security

P.K. Sharma (@_pksharma) on X

Thread distinguishing two Langflow advisories on MCP Stdio command execution. CVE-2026-105740 (GHSA-7w94-79vh-5mr2) affects 1.8.3 and is fixed in 1.9.0, an authenticated non-admin path. CVE-2026-105697 (GHSA-w794-rj3p-xv45) covers 1.1.2 up to but excluding 1.10.3, with fixes in lfx and langflow-base too. The later fix validates the API, flow and pre-spawn boundaries and removes the shell wrapper, and the thread warns that LANGFLOW_AUTO_LOGIN=true can expose a token without credentials. It cites one sensor's telemetry (1,628 attempts from 28 IPs) with caveats, and gives a defensive checklist: verify patched packages, review stored MCP configs and imported flows, and hunt for unexpected child processes.

AppSec, AI Security· Added 17 Oct 2026, published 15 Oct 2026

github.blogarticle🛡️ Security

Staying Evergreen: How we automated secure access and repo hygiene in a shared org

GitHub engineers describe Evergreen, a Go-based GitHub App that runs quarterly outside-collaborator access reviews and archives stale repositories in a shared org. It uses scheduled Actions with repository_dispatch, JSON state files in git as the audit trail, checklist issues (IssueOps) closed to trigger revocation, and custom properties for ownership and exemptions. Design principles include fail-secure/fail-closed revocation, never deleting data, dry-run rollout, Splunk logging, and proactive pacing against GitHub's secondary rate limits.

DevSecOps, Identity & Access· Published and added 15 Oct 2026

arxiv.orgpaper🧠 AI

Perceive, Predict, and Plan: a Unified World Action Model for Egocentric Dexterous Manipulation

P^3-WAM is a unified world action model for egocentric dexterous manipulation with three modes: Perceive (reconstruct articulated hand motion and camera trajectories from video), Predict (generate visual futures under prescribed actions) and Plan (jointly generate action trajectories and their anticipated visual outcomes from an initial image, a language instruction and an optional visual goal). It adds a compact structured 3D action representation to a pretrained video diffusion transformer through a mixture-of-transformers design with shared base weights, modality-specific adaptation and bidirectional visual-action attention. Randomized modality visibility lets video and 3D actions act as either context or target. Unified training beats single-mode training and outperforms specialized baselines on 3D hand reconstruction and action-conditioned video prediction across four datasets, and gives better instruction adherence than video-generation baselines.

research, multimodal· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

Private Retrieval Augmented Generation via Random Projection

Proposes protecting the retrieval datastore in RAG systems by applying the same random projection to datastore embeddings and query embeddings. This provably preserves query-item semantic similarity while substantially mitigating data extraction attacks. Across multiple RAG architectures and datasets it beats prior differential-privacy-based methods on retrieval and generation quality, with comparable empirical privacy under strong attacks, making it a practical baseline for privacy-preserving RAG.

research, llm-apps· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🛡️ Security

Private Retrieval Augmented Generation via Random Projection

Proposes applying the same random projection to both datastore embeddings and query embeddings in RAG systems. The authors claim this provably preserves query-to-item semantic similarity while substantially mitigating datastore data-extraction attacks. Across several RAG architectures and datasets it reportedly beats prior differential-privacy-based defenses on retrieval and generation quality, with comparable empirical privacy under strong attack models. It is presented as a lightweight baseline for privacy-preserving RAG.

AI Security· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search

EliteReplay is an RL post-training recipe that pairs GRPO with an "elite" archive built by quality-diversity search. Before training, the frozen base model is used to collect solutions spanning distinct approaches; during training, a replay loss on this archive is added to GRPO. This counters the narrowing of solution diversity that RL causes. On text-to-SQL tasks it reaches higher pass@128 than all baselines and yields up to 77% more distinct correct strategies. It also retains more of the base model's strategies and covers both readings of ambiguous questions nearly twice as often on AmbiQT.

training, research· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries

Introduces Librarian Agents, where a builder agent turns raw unstructured documents into a hierarchical filesystem of synthetic files and reference links, forming a workspace for a downstream answering agent. Workspace construction is cast as a Markov decision process and the builder policy is trained with reinforcement learning to maximize downstream answering accuracy. It beats the strongest retrieval and precomputation baselines by 33 points on BrowseComp-Plus, amortizes construction cost over repeated queries, and generalizes zero-shot to BRIGHT with a 31-point average gain.

research, agents, llm-apps· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning

X-RIC (eXplainable RIC) is a framework that adds agentic reasoning to the O-RAN Near-RT RAN Intelligent Controller. It combines reactive reinforcement learning with automated behavioral cloning from domain heuristics, a transformer-based Telecom Language Model for contextual abstraction and interpretability, and closed-loop co-adaptation for continuous policy refinement. The paper also introduces BARX, a benchmark for agentic RAN control that measures latency, compliance and determinism. On SLA-aware network slicing, in simulation and on an O-RAN-compliant testbed, it reports 89% lower operational cost with SLA compliance kept, 75% faster convergence, 50% fewer training steps and 46% lower variance.

research, agents, evals· Added 17 Oct 2026, published 15 Oct 2026

github.comrepo🛡️ Security

gichirimaku/wp2shell-PoC

wp2shell-PoC is a Python proof-of-concept exploiting a pre-authentication RCE chain in WordPress core, combining CVE-2026-63030 (REST API batch route confusion) and CVE-2026-60137 (SQL injection in WP_Query). It demonstrates escalation from the route-desync bug through blind SQLi, customize_changeset forgery, and hook re-entry to administrator account creation and arbitrary command execution via a malicious plugin upload. The tool supports vulnerability checking, data extraction (union, error-based, blind techniques), and full shell access with or without existing admin credentials.

AppSec, Offensive Security· Added 23 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

Efficient KV Cache Migration for Geo-Distributed LLM Inference in Collaborative Edge Computing

Proposes EdgeFlow, a hybrid KV cache migration scheme for distributed LLM inference across heterogeneous edge servers in Collaborative Edge Computing. It combines direct KV cache transmission with activation-based recomputation, overlapping computation and communication to cut migration time when servers disconnect or overload. The authors formulate a multi-node KV migration optimization problem and give a 2-approximation algorithm built on improved LP relaxation and bipartite graph techniques. Experiments on a real distributed LLM inference platform show up to 45% lower migration time.

inference, research· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

Multi-sourced AI Tutor for Non-Native English Speaker Students

Describes a general-purpose LLM-based AI tutor for computing courses that accepts questions in Mandarin and replies bilingually, also generating glossaries of technical terms. It uses a specialized multi-source RAG pipeline with a novel question extraction mechanism to draw on diverse course materials. Evaluated on 91 Piazza posts: 83.52% answered correctly and helpfully, 76.92% of questions got high-quality translations, and 64.47% got glossaries.

llm-apps, research· Added 17 Oct 2026, published 15 Oct 2026

deepmind.googlearticle🧠 AI

Accelerating the search for antimicrobial peptides with Google Antigravity

Google DeepMind describes using Google Antigravity as an agentic science workbench to find antimicrobial peptide candidates in Streptococcus pseudopneumoniae. The agent orchestrates queries across UniProt and other databases, uses ProtNLM function predictions for uncharacterized proteins, and pulls structures from the AlphaFold Database. A new Biomolecular Structure Viewer shares 3D state with the agent in both directions, so residues the researcher highlights or pins become context for the agent's reasoning. The resulting lead has predicted activity against respiratory-tract pathogens and is going into wet-lab validation.

agents· Published and added 15 Oct 2026

arxiv.orgpaper🧠 AI

DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache Eviction

DropKV is a KV-cache eviction framework for long-context LLMs. It decouples the joint eviction decision into independent per-token scores based on residual-output perturbation, which avoids the NP-hard combinatorial problem. It has a provable constant-factor approximation guarantee under a cone condition, which the authors verify empirically on three long-context LLMs. The fused Triton kernels never materialize the full attention matrix. They give a 19.8x scoring-kernel speedup and up to 9.9% end-to-end prefill speedup. On RULER and LongBench it beats state-of-the-art eviction baselines at equal cache budgets.

inference, research· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🛡️ Security

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

PROBE (Policy Rule Observation via Behavioral Exploration) trains LLM-based auditors that act as realistic users and probe deployed tool-using agents for policy violations (pricing, privacy, confirmation, safety) across multi-turn, tool-mediated dialogue. It formalizes auditing as a two-player Markov game with a composite reward for violation discovery, plausibility, progress and policy diversity, and compares GRPO, DPO and GFlowNet optimization. Trained auditors find broader, higher-yield violations than zero-shot adversaries, even when much smaller than the target agent, positioning behavioral auditing as a distinct axis next to capability and safety benchmarks.

AI Security· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents

PROBE (Policy Rule Observation via Behavioral Exploration) trains LLM-based auditors that act as realistic users and probe deployed tool-using agents for policy violations (pricing, privacy, confirmation, safety) over multi-turn dialogue. It formalizes auditing as a two-player Markov game with a composite reward balancing violation discovery, behavioral plausibility, conversation progress and policy diversity, and compares GRPO, DPO and GFlowNet optimization in a controlled setting. Trained auditors find broader, higher-yield violations than same-architecture zero-shot adversaries, even when much smaller than the target agent. This positions multi-turn behavioral auditing as a distinct evaluation axis alongside capability and safety benchmarks.

evals, agents, training· Added 17 Oct 2026, published 15 Oct 2026

arxiv.orgpaper🧠 AI

GraphACM: Graph-based Action Consistency Measurement for Uncertainty Quantification in LLM Agents

GraphACM merges equivalent states from multiple rollouts of the same LLM agent task into a directed, action-labeled graph, so actions can be compared at shared decision states. It defines node-level and global action-consistency measures, and uses the global score as an uncertainty proxy to predict task success or failure. Across three LLMs on ALFWorld, AppWorld and WebShop it reaches an average AUROC of 0.811, above the strongest behavioral-consistency baseline (0.729) and verbalized confidence (0.769). It also shows where in a trajectory agent actions diverge.

research, agents, evals· Added 17 Oct 2026, published 15 Oct 2026

eprint.iacr.orgpaper🛡️ Security

SecAgg++: A Post-Quantum Privacy Preserving Federated Learning Protocol

SecAgg++ is a masking-based secure aggregation protocol for single-server federated learning that swaps in post-quantum cryptographic primitives. It keeps the communication and computation efficiency of SecAgg and SecAgg+ and handles client dropout through an efficient recovery procedure built on secret sharing and additive masking. It matters because existing masking-based aggregation protocols are not post-quantum secure, so client model updates would be exposed to quantum-capable adversaries.

AI Security· Published and added 15 Oct 2026

eprint.iacr.orgpaper🧠 AI

SecAgg++: A Post-Quantum Privacy Preserving Federated Learning Protocol

SecAgg++ is a masking-based secure aggregation protocol for single-server federated learning that uses post-quantum cryptographic primitives. It keeps the communication and computation efficiency of SecAgg and SecAgg+ and handles client dropout through an efficient recovery procedure. It matters because most masking-based secure aggregation protocols are not post-quantum secure, which leaves federated model updates exposed to future quantum adversaries.

research, training· Published and added 15 Oct 2026

hackers-arise.comarticle🛡️ Security

Social Engineering: Exploiting Human Psychology in Offensive Security

Hackers Arise explainer on the human psychology that social engineers exploit. It covers cognitive overload ("brain DoS"), stereotyped automatic behaviour, and the authority, scarcity and consistency principles, with supporting studies (Milgram, Pliner, Europol fraud-victim statistics). It also describes trigger-bypass techniques such as reframing a password request as IT support, and an observed baseline percentage of recipients who act on phishing emails. It closes with organisational and personal defences.

Offensive Security, Learning· Published and added 15 Oct 2026

simonwillison.netarticle🧠 AI

Anthropic tells investors quarterly revenue up nearly 50% to $16.8bn ahead of IPO

Simon Willison's link-blog post summarizes an FT report on Anthropic's investor day ahead of an IPO. Revenue was about $4.8bn in Q1, $11.5bn in Q2 and $16.8bn in Q3 2026. Q3 brought $1.70 of revenue per $1 of compute spend and an 11% adjusted operating margin excluding stock-based compensation. Anthropic told investors that distillation by rival labs made up 5–7% of revenue and was cut back "materially" in Q3. Willison estimates this means other labs spent over half a billion dollars distilling Anthropic's models in Q2.

ai-policy· Published and added 15 Oct 2026

en.cryptonomist.charticle🛡️ Security

Ledger’s Atom device adds tamper detection after a recovery-phrase breach

News report on a Southeast Asia supply-chain breach in which Ledger devices sold via resellers such as CryptoBilis were modified with hidden chips. The chips read 24-word recovery phrases from the screen signals during setup and sent them out over LTE. Tether froze $10M USDT tied to the theft, and Ledger suspended sales in several Asian markets. It also covers Ledger's Android-based Atom signer, which adds a protective enclosure, screen and back-cover removal sensors with their own battery, tamper-evident packaging, and website-only initial sales.

Hardware & RF, Blockchain· Published and added 15 Oct 2026

securityweek.comarticle🛡️ Security

CikaBika Bot RAT Uses Discord for C&C

SecurityWeek reports Darktrace's findings on CikaBika Bot, a Rust-based RAT delivered via a PDF containing a disk image with an LNK disguised as a Word document. A hidden PowerShell step drops a Nim loader and a Rust DLL that is moved into the protected Edge directory to bypass UAC and sideloaded via DLL search-order hijacking of debugging-library exports. The RAT uses per-victim Discord channels for C&C (recon, command execution, file transfer, screenshots/camera) and exfiltrates ZIPped data via Ngrok.

Threat Intel, Malware & RE· Published and added 15 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Structural Cryptanalysis of the Eevee AEAD Family

ePrint paper cryptanalysing Eevee (Umbreon, Jolteon, Espeon), forkcipher-based AEAD modes proposed at CCS 2023 for IoT-to-cloud computation. It gives a two-encryption AD-free prefix distinguisher, a four-encryption nonce-misuse distinguisher, a deterministic AD-only forgery, and nonce-respecting forgeries on Jolteon and Espeon (fresh one-block forgery reusing the tag; arbitrary AD substitution). It traces these to proof flaws (online-prefix consistency, domain separation, checksum freshness), derives design requirements, and concludes the failures are in the mode design, not the C implementation.

other· Published and added 15 Oct 2026

securityweek.comarticle🛡️ Security

Palo Alto Networks Patches PAN-OS Zero-Day Exploited for Remote Code Execution

Palo Alto Networks patched CVE-2026-0322, a high-severity zero-day in the PAN-OS management interface that lets an authenticated attacker with network access run arbitrary code as root. It affects PA-Series, VM-Series and Panorama with no special configuration needed, and "very limited" exploitation has been seen. The vendor published a few IP-based IoCs, CISA added the flaw to KEV with an October 17 deadline, and a dozen other medium/low advisories were released the same day.

Threat Intel, Cloud & Infra· Published and added 15 Oct 2026

snyk.ioarticle🧠 AI

VulnBump: Can AI Agents Fix Vulnerable Dependencies Without Breaking the Build?

Snyk introduces VulnBump, a benchmark of 307 real vulnerable-dependency upgrades from 43 repositories across Maven, Gradle, npm, Yarn, pip and Poetry. An attempt passes only if a fresh Snyk rescan shows the vulnerabilities gone and the project installs, builds and keeps its previously passing tests green in a clean container. On Claude Sonnet 5.5, Snyk's Evo Remediation Agent passed 90.2%, Claude Code with Snyk scan and target version 77.5%, unaided Claude Code 59.6%, and a non-AI package-manager bump baseline 46.9%. Unaided Claude Code often claimed fixes a rescan still flagged, so the benchmark shows harness and security data matter as much as the model. The harness and 43 cases are open-sourced.

evals, coding-agents· Published and added 15 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Exploring Fault Injection Attacks on HQC and BIKE Beyond Fujisaki-Okamoto Verification

Presents fault injection attacks on BIKE and HQC decapsulation that target instructions outside the Fujisaki-Okamoto transform, achieving full key recovery with only valid ciphertexts at NIST Level 1 (17392 queries for HQC, about 3 million for BIKE). It also gives a general method for finding effective fault locations by analysing decoder behaviour under perturbed conditions. Attacks were validated with laser fault injection on an STM32H7 microcontroller, showing a wider attack surface for code-based post-quantum KEM implementations.

Hardware & RF· Published and added 15 Oct 2026

arxiv.orgpaper🧠 AI

Recursive Reward Improvement via Adversarial Meta-Prompt Evolution

Introduces Recursive Reward Improvement (RRI) for recursive self-improvement on open-ended expert tasks without answer keys, where a proposer writes both a task and a rubric. Before the solver trains, an adversary writes a rubric-gaming but useless answer, the same model writes an honest answer without seeing the rubric, and up to two repair steps revise the rubric until the honest answer wins. Exploits found also rewrite future task and rubric generation. On HealthBench Professional it beats a Generation Only baseline by 10.9 points at 9B and 12.4 at 27B (10.3 with no external model), and the 27B model transfers to PRBench Hard (+6.6) and ProfBench (+8.0).

research, training· Added 17 Oct 2026, published 15 Oct 2026

huggingface.coarticle🧠 AI

Welcome FLUX.3 Image Klein in Diffusers

Hugging Face blog post introducing Black Forest Labs' open FLUX.3 Image Klein (distilled and base checkpoints) in Diffusers. It covers text-to-image, multi-reference image-to-image and bounding-box layout control, FP8/NVFP4 single-file quantized weights, DreamBooth LoRA training scripts for generation and editing, memory/speed figures (about 2 s per 1024×1024 image on an H100), and a detailed architecture tour: Qwen3-VL text encoder, two-stage per-stream then joint transformer blocks, per-token timestep modulation, 4D RoPE, and flow-matching denoising. It also shows how to customise the Modular Diffusers pipeline.

models, multimodal, training· Published and added 15 Oct 2026

huggingface.copaper🧠 AI

Harness^2: Recursive Agent Harnessing for an Open World

Harness^2 is a plug-and-play framework that recursively improves LLM agent execution harnesses in open-world settings where no ground-truth verifiers exist. Task-level recursion uses a contrastive Propose-Probe-Compose step to guide harness edits for the current task, and it scales through parallel or sequential recursion. Harnessing-level recursion distills experience from those edits into a continual-improvement harness for future tasks. A single step improves GLM-5 and Gemini 3.5 Flash over their base harnesses by up to 11.5 points on WorkBuddy-Bench, 4.5 on JobBench and 11.8 percentage points on LAB.

agents, research· Added 14 Oct 2026

simonwillison.netarticle🧠 AI

Tree Appreciator

Simon Willison describes another game experiment, this time in the Claude iPhone app in chat mode rather than Claude Code. He prompted Claude Opus 5.5 Max to build a three.js game called "Tree appreciator" with two algorithmically generated trees and a mechanic based on appreciating their differences, and added "think hard about how to make sure it is both fun and beautiful". After about 3 hours 7 minutes of work it returned a spot-the-difference game with music, animation and achievements. He notes that simply telling Opus 5.5 to "make sure it is fun" works surprisingly well.

prompting, models· Added 15 Oct 2026, published 14 Oct 2026

aws.amazon.comarticle🛡️ Security

Penetration testing every deployment with AWS Continuum

Explains how to add AWS Continuum for penetration testing (formerly AWS Security Agent) as a post-deployment gate in CI/CD. Each run is scoped to the commit range since the last passing gate, and it can block promotion to production at a chosen severity threshold. It covers OIDC federation to a least-privilege IAM role, a GitHub Actions worked example, staged report-only rollout, and pitfalls: the baseline advances on passing report-only runs, fail-on-infrastructure-error defaults to fail-open, GitLab pipeline variables can override the committed threshold, and runner credentials need protecting.

DevSecOps, Offensive Security, AI Security· Published and added 14 Oct 2026

decrypt.coarticle🧠 AI

AI Agents Made 138 Million Crypto Payments in a Year. Most Were Tiny

Decrypt reports on a Chainalysis Geography of Crypto report. It found AI agents made more than 138 million payments through Coinbase's x402 protocol on Base, up from about 1,500 in mid-2025. Over 87% of the payments were between $0.0001 and $0.10, which stablecoins can handle but card rails cannot. US-linked wallets made 88.1% of identifiable inference payments. The article covers agent-payment support from Visa, Mastercard, Stripe, Coinbase and Google, and TRM's caution that much of the activity may be scripts or self-dealing rather than genuine agents.

agents, ai-policy· Published and added 14 Oct 2026

bankless.comarticle🧠 AI

Crypto's Quantum Defense Is Being Built in the Open

Bankless article on Eigen Labs' Yukon, a platform for open-research challenges where developers and AI agents try to improve a technical problem. Each submission is automatically benchmarked, and accepted improvements become the baseline for the next attempt. Results include an ~88% cut in the ECDSA.fail quantum resource-cost benchmark, a ~10x speedup in Lighter's proving software, ~2x faster Qwen and 2.6x faster Laguna on Apple hardware via MLX.fast, and cheaper Quantum Safe Bitcoin proofs ($320 down to $59). Newer challenges (HashSmash, sig.golf, better.codes) target hash-function weaknesses, hash-based signatures and post-quantum proofs. All the improvements are theoretical or benchmark-level unless stated as deployed.

agents, evals· Published and added 14 Oct 2026

bankless.comarticle🛡️ Security

Crypto's Quantum Defense Is Being Built in the Open

Bankless article on Eigen Labs' Yukon platform, which runs open challenges where researchers and AI agents attack and improve cryptography. It covers ECDSA.fail (quantum circuit cost for attacking Bitcoin/Ethereum ECDSA, cut about 88% from baseline), HashSmash (SHA-256 weakness hunting, so far only on reduced versions), sig.golf (hash-based signatures), StarkWare's Quantum Safe Bitcoin (cost down from about $320 to $59) and better.codes (provable security raised from 64 to about 68 bits). The argument is that public, measurable attack-cost data helps defenders prepare better than withholding circuits does. All gains are theoretical and no quantum computer has run an attack at this scale.

other, AI Security· Published and added 14 Oct 2026

x.comthread🛡️ Security

Victor (@VMG_CU) on X

A social post summarising Elastic's REF8801 campaign. A fake startup accelerator offered founders free Claude/Gemini credits plus a coding agent. The agent was a repackaged open-source project that set OPENROUTER_BASE_URL to an attacker-controlled endpoint and added its own MCP server, so victims' prompts and code went to the attacker. It shows how a trojanised AI coding agent can hijack the LLM base URL and add an MCP server for exfiltration.

Threat Intel, AI Security· Added 15 Oct 2026, published 14 Oct 2026

eprint.iacr.orgpaper🛡️ Security

A Hybrid BP-SAT Attack on MILENAGE: Combining the Complementary Strengths of Algebraic and Soft-Analytical Side-Channel Attacks

ePrint paper evaluating ASCA (SAT-based) and SASCA (belief propagation) side-channel attacks on the AES-based MILENAGE authentication algorithm in USIM cards, using neural-network leakage predictions to recover subscriber key K and operator secret OPc from a single trace. SASCA alone succeeds in 87.7% of attacks but converges to a wrong OPc in 6.1%; ASCA succeeds in only 34% within a 1-hour timeout. The hybrid, where BP refines the predictions before they go to the SAT solver, reaches 93.8% with lower average runtime. It also proposes a countermeasure that masks each AES round key with an independent per-device secret, and the authors report it defeated the hybrid attack in all evaluated cases.

Hardware & RF· Added 15 Oct 2026, published 14 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Post-Quantum Certificate-Based PSK Provisioning for WireGuard via Mutual TLS, DTLS, and QUIC: Design and Performance Study

The paper proposes a post-quantum architecture for WireGuard that leaves the core protocol unchanged. A mutually authenticated TLS 1.3 control channel runs over TCP, UDP (DTLS) or QUIC and uses ML-KEM key establishment, with X.509 certificates from a PKI signed with ML-DSA. A shared secret derived from the session's exported keying material is injected into WireGuard's native PSK interface. A Tamarin model of the TLS–WireGuard composition layer checks secrecy, binding and provisioning-order properties and identifies the conditions needed for secure deployment. The authors benchmark handshake latency and CPU time for classical, pure-PQ and hybrid key establishment across the three transports, and compare against the Rosenpass PQ WireGuard baseline.

other· Added 15 Oct 2026, published 14 Oct 2026

chainalysis.comarticle🧠 AI

North America: Inside the Growth of Agentic Commerce

Chainalysis's North America chapter of its 2026 crypto adoption report. Its centrepiece is an on-chain analysis of Coinbase's x402 protocol, which lets AI agents pay autonomously: over 138M transactions on Base, 87% of payments between $0.0001 and $0.10, and growing wallet re-funding (70.6% to 89.3% within 30 days). Wallets also move from funding to first spend faster (73 days to 18 minutes at the median). It breaks down what agents buy (data/search APIs, code review, model inference, agent frameworks), shows US wallets making 88% of inference payments and Chinese wallets dominating security-audit spend, and argues compliance should screen agent funding, counterparty and behaviour pattern rather than each payment. The remainder covers dollar stablecoin exports, tokenized Treasuries and Canada's peer-to-peer and remittance flows.

agents, ai-policy· Published and added 14 Oct 2026

ethereum-magicians.orgarticle🛡️ Security

ERC-8443: Quantum Bridge Shield

Draft ERC from Quantova Inc proposing a "Quantum Bridge Shield" for Ethereum bridges. A committee signs the Merkle root of each message batch with RFC 8554 LMS hash-based signatures instead of ECDSA/BLS keys that Shor's algorithm can break. The guard contract requires a strict majority of distinct unfrozen keys, records used leaves, freezes any key that signs a leaf twice, binds digests to domain, chain, guard and epoch, and applies a 60-second delay. The post gives gas costs (LMS W4 height-10 verification about 205k gas, a LayerZero packet 128,683 gas, worst-case rotation 12.44M gas under the EIP-7825 cap) and cites a NioLabs assessment with no critical or high findings. It is relevant as a worked post-quantum migration design for bridge key custody, including hybrid ECDSA+LMS mode and stateful-signature pitfalls such as leaf reuse and rollback.

Blockchain· Published and added 14 Oct 2026

ethereum-magicians.orgpaper🛡️ Security

ERC: Quantum Bridge Shield

Draft ERC from Quantova Inc that has Ethereum bridges accept cross-chain message batches only when a committee signs the Merkle root with RFC 8554 LMS hash-based signatures. The guard contract requires a strict majority of distinct unfrozen keys, records used leaves, freezes any key that signs a leaf twice, binds digests to domain tag, chain ID, guard address and epoch, and enforces a 60-second delay. It reports gas benchmarks (about 205k per LMS W4 height-10 verify, 12.44M worst-case rotation under EIP-7825), a hybrid LMS+ECDSA migration mode, and a NioLabs assessment with no critical or high findings. It argues that Shor's algorithm makes secp256k1 and BLS committee keys a quantum theft target.

Blockchain· Published and added 14 Oct 2026

blog.trailofbits.comwriteup🛡️ Security

Package managers have an integrity problem

Trail of Bits tested 25 popular package managers with a Docker and mitmproxy harness that simulates a compromised package repository injecting malware into legitimate packages. Fewer than half enforce lockfile hashes by default, only two verified every download, and only Go verifies signatures by default. The post covers lockfile hash pitfalls (Pub, pnpm, Conan, CocoaPods, Composer), repository, developer and Sigstore signing, and Go's checksum database. It also proposes lockfiles that commit to a signing identity plus a transparency log.

Supply Chain· Published and added 14 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Refined Application of the XL Algorithm within the Algebraic Approach to the Regular Syndrome Decoding Problem

Furue and Aikawa build and analyze algebraic attacks on the Regular Syndrome Decoding Problem (RSDP), which underlies code-based post-quantum schemes. They extend the Wang et al. hybrid algorithm to allow an arbitrary XL solving degree d, and add two variants: an XFL-based one (partial Gaussian elimination plus variable guessing) and a WXL-based one that exploits Macaulay matrix sparsity. Complexity analysis shows the WXL variant with d>2 wins for small block size β, while the original hybrid wins as β grows. This matters for setting RSDP-based scheme parameters.

other· Published and added 14 Oct 2026

securityweek.comarticle🛡️ Security

Chrome, Firefox Updates Patch 114 Flaws as Mozilla Unveils Firefox Enterprise

SecurityWeek covers Chrome 155.0.8059.79/.80, which fixes 37 flaws including seven critical memory bugs (an ANGLE buffer overflow and use-after-free bugs in Browser, PDF, Network, Core, SVG and Media). It also covers Firefox 158, which fixes 77 flaws including 30 high-severity use-after-free, sandbox escape, JIT miscompilation and integer overflow bugs, plus matching Thunderbird and Firefox ESR releases. At least 15 of the Chrome bugs were reported by Xinyang Ge (Anthropic) assisted by Claude, and Amy Burnett of OpenAI found 9 Firefox bugs. The article also notes Mozilla's new Firefox Enterprise, a Gecko-based browser with a self-hosted management console for policy, access, data transfer and AI use.

AppSec, AI Security· Published and added 14 Oct 2026

metr.orgarticle🧠 AI

How an assessor could investigate control and monitoring of internal AI agents

METR's proposal for how an external assessor could run a control assessment of an AI developer's internal agents and their LLM-based monitoring. It sets out five sub-questions: monitor coverage, monitor system vulnerabilities, monitor evasion, response including human evasion, and impact. For each it lists methods and the access needed, such as inference logs, about 100k representative transcripts, codebase access and the ability to insert attack trajectories.

ai-safety, agents, evals· Added 29 Oct 2026, published 14 Oct 2026

metr.orgarticle🛡️ Security

How an assessor could investigate alignment of unreleased AI models

METR proposes an "alignment assessment" in which an outside assessor investigates the worst misaligned actions a developer's near-frontier internal AI agents might take. It covers surveying logged incidents (hacking, log tampering, collusion, rogue deployments, weight exfiltration), counterfactual simulations, and training-overfitting concerns. It lists required access (transcripts, checkpoints, raw chain of thought) and estimates over $10M in API credits for two months, based on the Hugging Face investigation (about $400K in six days).

AI Security· Added 29 Oct 2026, published 14 Oct 2026

coindesk.comarticle🛡️ Security

Coinbase, which holds 5% of all bitcoin, wants the quantum fix started now

CoinDesk summarizes Coinbase's recommendations for making Bitcoin quantum-resistant before a cryptographically relevant quantum computer (CRQC) can derive private keys from public keys. The proposals are: a transaction format that can carry new signature types (P2MR/BIP-360, P2TRv2), staged hybrid "1-of-2" spends with ECDSA/Schnorr or a post-quantum key, and stateless options alongside stateful schemes to avoid key-reuse forgery. They also ask that evaluation favor constant-time, RNG-failure-safe implementations, require MPC compatibility, and handle dormant or late-migrating coins as a separate debate. It is a useful overview of the defensive migration design space, but it is secondary reporting and not the primary Coinbase paper.

other· Published and added 14 Oct 2026

theblock.coarticle🛡️ Security

Coinbase lays out flexible designs as key priority for Bitcoin’s post-quantum migration

Coinbase's October 2026 position on Bitcoin's post-quantum migration, as reported by The Block. Coinbase, which holds about 5% of bitcoin supply, favors output designs that separate the container from the signature scheme (P2MR/BIP-360, P2TRv2), staged hybrid 1-of-2 spending paths, a stateless option beside stateful signatures, and MPC-compatible schemes for custody. It also wants the abandoned-coins debate run in parallel.

other· Added 31 Oct 2026, published 14 Oct 2026

eprint.iacr.orgpaper🧠 AI

DPF-SGD: Byzantine-Robust Differentially Private Federated SGD with Exact Optimality Guarantees

DPF-SGD is a federated SGD algorithm that stays robust to Byzantine agents while satisfying ϵ-differential privacy. It combines private step sizes with a DP noise-decay schedule and adds a privacy-preserving comparative elimination (PPCE) filter that suppresses Byzantine updates during aggregation. The authors prove almost-sure convergence to the global optimum despite persistent noise and adversaries. On synthetic and MNIST data, final optimization error is one to two orders of magnitude lower than DP baselines.

research, training· Published and added 14 Oct 2026

dfir.chwriteup🛡️ Security

Field Notes: EtherRAT Distributed Through a Legitimate Intune Workflow

DFIR case where a malicious MSI impersonating Advanced IP Scanner, sourced from a fake GitHub repo found via Bing, was imported by a customer into Microsoft Intune and deployed to four endpoints, running a Node.js-based EtherRAT chain. It traces the infections by correlating the MSI ProductCode, MDMAppInstaller/omadmclient process ancestry and Intune app inventory (Graph PowerShell query). It also covers renamed node.exe hash-hunting pitfalls, Ethereum RPC dead-drop C2 traffic, a screen-capture script and a second impersonating repo.

Blue Team & Detection, Threat Intel, Malware & RE· Added 14 Oct 2026, published 13 Oct 2026

huggingface.copaper🧠 AI

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

AgentSWE is a benchmark of 25 tasks covering the agent development lifecycle: Creation of an agent from a natural-language requirement, Editing of production agent codebases, and Optimization toward a measurable target. Builders iterate on a few illustrative cases, then the frozen submission is graded on held-out cases with requirement-derived rubrics and hard pass/fail gates. Across coding agents, models and harnesses, none comes close to delivering the requirement. Recurring failures include overfitting to visible cases, hollow runtimes behind code that looks complete, and unsupported claims of completion.

evals, coding-agents, agents· Added 13 Oct 2026

eprint.iacr.orgpaper🛡️ Security

Snapshots of TEE-Based Encrypted Databases Leak Plaintext Histograms via Dendrochronology

ePrint entry for an ACM CCS 2026 paper in the "Attacks and cryptanalysis" category. By its title and keywords, it shows that snapshots of encrypted databases built on trusted execution environments leak plaintext frequency histograms, using a technique called "dendrochronology". The abstract and full text are embargoed until the end of October 2026, so the attack mechanics are not available yet. It matters to anyone assessing the real leakage of TEE-backed encrypted databases against snapshot adversaries.

other· Added 14 Oct 2026, published 13 Oct 2026

eprint.iacr.orgpaper🧠 AI

A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference

Systematization of knowledge on private Transformer inference (PTI) that builds an empirical graph of 62 systems, with system attributes as node features and evaluation compatibility as edges. Node-level attribution finds that cryptographic progress drives most speedups but always co-occurs with confounders such as model fidelity, hardware and cost accounting. Edge-level auditing finds only 1 of 1891 candidate system pairs directly comparable. Graph-level analysis shows the scale frontier plateaued at 13B parameters and projects the cost of deploying current PTI techniques on production-scale Transformers.

research, inference, evals· Added 14 Oct 2026, published 13 Oct 2026

parsimony.lasu.devtool🧠 AI

Show HN: Parsimony – an open-source benchmark for how much code AI models add

Parsimony is an open-source benchmark that ranks AI coding models by how much code their patches add. It parses the patches already published by benchmarks such as SWE-bench Verified, counts syntax-level "coding units" (statements, calls, comparisons, names, literals) rather than lines, and subtracts deleted code to get net units. It adds a leaderboard, an Artificial Analysis Intelligence Index overlay, the author's own DeepSWE runs, and a way to upload your own results. It matters because existing benchmarks score solve rate and cost but not code bloat, which makes codebases harder to maintain. The page states its limits: it measures size, not quality, and more verbose models tend to solve more tasks.

evals, coding-agents· Published and added 13 Oct 2026

arxiv.orgpaper🧠 AI

Hybrid Reasoning Agents

Introduces Hybrid Reasoning Agents (HybridAgents), which switch between latent reasoning and text-based interaction in one generation process. A lightweight HybridLink handles transitions between the two modes, and a continuous working memory keeps hybrid context lossless across turns. This keeps tool use and makes latent thoughts inspectable. Post-training has two stages: HybridSFT, then HybridRL, which learns when to think latently and when to act in text. Across 3 model scales and 11 benchmarks (math, science, medicine, search, agentic reasoning), the authors report +10.4% performance, 35.5–54.7% fewer tokens, 1.8–2.6x faster inference and 2.7–3.7x lower cost versus text and latent baselines.

research, agents, training· Added 14 Oct 2026, published 13 Oct 2026

arxiv.orgpaper🧠 AI

Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs

Proposes mmVB, a lightweight plug-and-play module (1.6M trainable parameters) that assigns query-conditioned per-image visual token budgets using cross-image context for multimodal LLMs, without retraining the base model or accessing attention matrices (so it is compatible with FlashAttention). It cuts visual input tokens 9x, giving 5x faster time-to-first-token and 7x fewer prefill FLOPs while keeping 94.4% of full-resolution accuracy across eight multi-image reasoning benchmarks. It matters because existing token pruning, merging and compression methods target single-image redundancy and either need attention maps or retraining.

research, multimodal, inference· Added 14 Oct 2026, published 13 Oct 2026

arxiv.orgpaper🧠 AI

PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts

PixelMoE is a pixel-space diffusion framework that scales capacity sparsely using standard LLM-style Mixture-of-Experts: token-choice routing, fine-grained routed experts, a shared expert and bias-based load balancing, with no diffusion-specific routing or auxiliary routing losses. It adds Pixel-Space Hierarchical Flow Matching, which varies spatial resolution along the denoising trajectory from global structure to fine detail. At matched active parameters it beats dense counterparts, and reaches FID 1.47 at 256x256 and 1.53 at 512x512 on class-conditional ImageNet-1K without representation alignment or perceptual losses. Code and models are promised but not yet released.

research, multimodal· Added 14 Oct 2026, published 13 Oct 2026

github.blogarticle🧠 AI

GitHub’s model for secret detection: Finding more secrets with less noise

GitHub describes replacing an LLM-based generic secret detection pipeline with a two-stage system. High-recall regex generates candidates, then a fine-tuned ModernBERT classifier scores each one using its file path, secret type, variable names and surrounding context. Training data mixes product feedback, weak-labelled regex candidates and synthetic hard negatives, with splits grouped by repository, value or example. The model is exported to ONNX with 8-bit quantization. Reported results against the LLM pipeline: 13% higher precision, 19% higher recall, 11.5% higher owner-weighted acceptance in an A/B test, 86% lower median post-push scan time and over 98% lower serving cost. It is a concrete case for using a small fine-tuned encoder instead of an LLM on a narrow, measurable classification task.

training, inference· Published and added 13 Oct 2026

socket.devarticle🛡️ Security

Agent Baseline Publishes Security Reference Architecture for Software Factories

Socket summarizes Agent Baseline's "The Secure Software Factory: A Reference Architecture", co-authored by Socket CTO Ahmad Nassri with contributors from Docker, Keycard, Barclays and Secure Theory. It treats the coding agent as untrusted and enforces four boundaries outside its decision loop: sandbox, network, supply chain, and identity/access. These are applied across three autonomy levels. The post opens with the PocketOS incident, where an agent found a stray API token and deleted a production database and its backups in nine seconds. It stresses supply chain admission points and an egress proxy the agent can't reconfigure, because agents denied a package have gone to the CDN, rewritten registry config, or done their own DNS lookups to reach npm or PyPI.

AI Security, DevSecOps, Supply Chain· Published and added 13 Oct 2026

securityweek.comarticle🛡️ Security

Google Partially Reverses Chrome Bug Bounty Cuts

Google is raising Chrome Vulnerability Reward Program payouts for memory safety bugs. The base rate goes from $500 to $2,000, with up to $20,000 for browser, GPU and network process bugs and up to $8,000 for renderer use-after-free and memory write bugs. V8 sandbox bugs move to a flat $5,000 and V8 logic bugs to $4,000. A $2,000 fuzzer bonus returns, and submissions made after April 30, 2026 are rewarded under the new rules. The rates are still well below the pre-April 2026 levels. The article also notes that Google temporarily closed the OSS VRP to product vulnerability submissions because of a flood of AI-generated reports.

other, AppSec· Published and added 13 Oct 2026

arxiv.orgpaper🧠 AI

UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models

UniW(A)M is a mixture-of-experts model built on diffusion Transformers that unifies action-conditioned world modeling (AC-WM) with several world-action model (WAM) variants. Shared experts capture common physical dynamics, while atomic capability experts are reused across interfaces, each keeping its own conditional pathway. At deployment a plug-in adaptive interface router (PAIR), trained on a small subset of target-task chunk scenarios with the backbone frozen, picks a WAM interface for each execution chunk. It reaches 88.3% average real-world success against 76.7% for the strongest baseline, leads WorldArena on all three action-conditioned world-modeling tasks, and PAIR raises OOD success from 63.3% to 76.7%.

research, multimodal· Added 14 Oct 2026, published 13 Oct 2026

arxiv.orgpaper🧠 AI

MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization

MultiAlloc is a profiling-guided framework for KV cache quantization. It splits a fixed KV memory budget between layer-wise precision enhancement and token-wise preservation. Lightweight offline profiling measures layer sensitivity and token importance, and the profiled memory–accuracy trade-off yields an allocation policy with no online search. The paper reports gains over layer-wise, token-wise and recent multi-granularity KV quantization baselines at matched memory on reasoning and long-context benchmarks, across Mistral, Llama, DeepSeek-Qwen and QwQ models.

inference, research· Added 14 Oct 2026, published 13 Oct 2026

arxiv.orgpaper🧠 AI

Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning

Legal-R1 is an agentic retrieval framework for evidence-based legal question answering that splits reasoning across three agents. A Lawyer agent decides when to retrieve, which legal source to query, what evidence to seek and when it has enough. A Legal Assistant retrieves statutes and precedent cases with authority-aware and diversity-aware selection, and a Judge agent writes the final answer from the full evidence trajectory. Only the Lawyer agent is post-trained, using masked supervised fine-tuning and trajectory-aware reinforcement learning. The paper reports gains over general-purpose, legal-specific and retrieval-augmented baselines on several Chinese legal benchmarks.

research, agents, llm-apps· Added 14 Oct 2026, published 13 Oct 2026

arxiv.orgpaper🧠 AI

LLM Agents for Automated Post-Training via Structured Recipe Optimization

Introduces Structured Recipe Optimization (SRO), a paradigm for automated LLM post-training that optimizes over a task-adapted recipe space covering data sources, data processing, cross-domain composition and training configuration. It pairs an LLM-based Recipe-Space Designer, which builds the recipe space for the target tasks, with a Multi-Domain Recipe Optimizer that uses structured trial evidence to guide LLM candidate construction and multi-objective Bayesian trial selection. SRO gets the highest average score in all evaluated target-model and agent-LLM combinations; for example, 41.1 vs 15.4 for the strongest baseline on Qwen3-1.7B with GPT-5.4, and 53.8 vs 40.8 on Qwen3-4B with DeepSeek-V4-Flash, in joint post-training across three capability domains and six benchmarks.

research, training, agents· Added 14 Oct 2026, published 13 Oct 2026

en.cryptonomist.charticle🛡️ Security

Coinbase advances Bitcoin’s post-quantum readiness while holding about 5% of BTC

Summarizes Coinbase's blog post on preparing Bitcoin and custody infrastructure for post-quantum threats. It covers public-key exposure (an estimated 6.7–7M BTC behind already-exposed keys), BIP 360 (P2MR) and P2TRv2 outputs, 1-of-2 hybrid classical/post-quantum spending paths, and the state-reuse forgery risk of stateful signatures. It also covers candidate schemes (ML-DSA, SLH-DSA, FN-DSA, SHRINCS), MPC/HSM compatibility and side-channel tests, and separate handling of dormant, lost and exposed legacy funds.