Skip to content

278 results for β€œTRACE”

ListGrid
What you seeeverything
RecentOldestAddedA–Z
All types278Articles93Papers92Write-ups55Repos22
Tools5Talks4Threads4Advisories2Courses1
β€œTRACE”
huggingface.coarticle🧠 AI

Palette: teaching a small model to build decks in your design language

Palette is an IBM Research fine-tune of a 20B open-weight model that builds slide decks in the IBM Design Language. A designer role writes a JSON brief and a coder role writes pptxgenjs code per slide, both served by one LoRA adapter. Training used about 1000 synthetic decks (roughly 10,000 slides) with counterfactual reasoning traces. A render-and-repair harness adds 3.5 points on PresentBench. Palette ranks first on Economics and Education and second on the three-domain mean (59.7 vs NotebookLM 60.8).

LoRApptxgenjsHugging Face
IBM ResearchIBMPalette+3

training, models, evalsΒ· Published and added 3 Nov 2026

en.cryptonomist.charticleπŸ›‘οΈ Security

BTCPay Server vulnerability: about $1.63M traced to theft-linked addresses

BTCPay Server's 2 November 2026 incident update describes attackers logging in as administrator on servers running version 2.4.1 or earlier and sweeping on-chain hot wallets. Bitquery traced about $1.63M (18.38 BTC and 3,405 LTC) to two addresses, across 682 sweeps from 30 October. The project advises migrating to a new server with a fresh seed, installing 2.4.7 and preserving logs. How admin access was gained is not explained.

BTCPay ServerLNDBitcoin+1
BitqueryCryptonomist

Blockchain, Threat IntelΒ· Published and added 3 Nov 2026

latent.spacetalk🧠 AI

Building AI for Lawyers - Jacob Lauritzen, CTO of Legora

Latent Space podcast episode with Jacob Lauritzen, CTO of Legora, on building AI agents for lawyers. He describes evals built from RL environments such as a 10,000-file data room because traces cannot be read, routing across models, source-linked citations, and a few shared primitives (Tabular Review, lists, intake). Also covers legal engineers versus forward deployed engineers, Azure-only hosting, and the billable hour. Based on the first 40,000 characters of the transcript.

AzureSlackTabular Review+4
LegoraJacob LauritzenLatent Space+12

agents, evals, llm-appsΒ· Published and added 2 Nov 2026

chainalysis.comarticleπŸ›‘οΈ Security

Disrupting the Mercado Bitcoin Attack: How Chainalysis Led the Freeze of Nearly $10M in Stolen Funds

Chainalysis describes its response to the 2 November 2026 hack of Mercado Bitcoin, Brazil's largest crypto exchange, where an attacker drained about $49 million across 17 blockchains. Investigators traced the funds, contacted law enforcement within 30 minutes and worked with Paxos, Anchorage Digital, Ripple, Circle and Tether. Tether froze over $9 million in USDT, nearly $10 million in all. The post does not explain how the attacker got in.

TetherBitcoinEthereum+2
Mercado BitcoinChainalysisCircle+3

Threat Intel, Blue Team & DetectionΒ· Published and added 2 Nov 2026

latent.spacetalk🧠 AI

Building Legal Agents When You Can't See the Data - Jacob Lauritzen, CTO of Legora

Latent Space interview with Jacob Lauritzen, CTO of Legora, on building a legal agent when the company cannot read customer traces. It covers simulated test "worlds" built by engineers and lawyers, a citation fix that went from 70% to 99% with a model release, paraphrased traces, and running on Azure. It also covers Tabular Review, intake bots, forward-deployed engineers and the harness.

AzureSlackTabular Review+5
LegoraLatent SpaceWexler+9

agents, evals, llm-appsΒ· Published and added 2 Nov 2026

en.cryptonomist.charticleπŸ›‘οΈ Security

Elliptic traces $2.2M of Binance hack funds through Bitcoin mixing

Elliptic's 2 November 2026 analysis reports the first laundering of proceeds from the 29 October 2026 Binance hack. By 1:02 a.m. ET it counted 18 WabiSabi coinjoin transactions, funded by bitcoin routed out of Tron and bitcoin bought with swapped ETH. The 18,270 BTC stolen directly had not moved. Elliptic names stablecoins and centralized cashout platforms as the remaining chokepoints. The page gives no addresses, transaction IDs or tracing method.

BitcoinEthereumTron+1
EllipticBinanceFBI+2

Blockchain, Threat IntelΒ· Published and added 2 Nov 2026

bleepingcomputer.comarticleπŸ›‘οΈ Security

FBI links $6.3 billion Binance crypto heist to North Korean hackers

The FBI attributed the roughly $6.3 billion Binance theft of about 29 October 2026 to North Korea's TraderTraitor (Lazarus Group, Jade Sleet, APT38). Binance traced the breach to a compromised DevOps engineer's laptop that gave access to a service container used to submit unauthorized withdrawals across ten blockchains. The FBI published 628 laundering addresses and linked the group to earlier thefts at Bybit, DMM Bitcoin, Bitget and Drift.

EthereumBitcoinSolana+3
TraderTraitorLazarus GroupDPRK+14

Threat Intel, BlockchainΒ· Published and added 1 Nov 2026

latent.spacearticle🧠 AI

Agents Prompt People: Using Agents for Long-Horizon Financial Work

Latent Space podcast write-up of an AI Engineer New York interview with Aman Singh, lead AI Engineer at Arca, an AI-native wealth management firm. Arca runs agent tasks lasting up to ten days, uses a per-client memory system, and owns its harness, which routes tasks to models (mainly Claude) by internal benchmarks. Safety rules are deterministic, trading stays with human advisors, and a meta-agent uses advisor feedback and traces to improve the harness.

ClaudeLLM
ArcaAman SinghAnthropic+6

agents, ai-infraΒ· Published and added 31 Oct 2026

theblock.coarticleπŸ›‘οΈ Security

Hackers hijack a dozen DeFi websites, all registered with Name.com, and steal about $138,000

Twelve DeFi websites, including Flap, Kintsu, Pickle Finance and Origami Finance, were hijacked on 30 October 2026 and served the Step Drainer kit. All 12 domains use Name.com as registrar, and 10 were suspended. The Block traced about $138,000 stolen to three EVM wallets, excluding Solana and Aptos losses. Kintsu and Origami blame Vercel. Projects say their onchain contracts were untouched.

VercelEthereumSolana
Step DrainerName.comFlap+5

Threat Intel, BlockchainΒ· Published and added 31 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Binance Hack: Everything You Need to Know About the Biggest Crypto Heist in History

Decrypt's explainer on the roughly $6.4 billion theft from Binance hot wallets across about 10 blockchains. Binance traced it to a compromised DevOps engineer laptop plus further breach points, and on Ethereum the attacker used 50 pre-signed EIP-7702 authorizations to turn a hot wallet into a sweeper. Chainalysis and TRM Labs attribute it to TraderTraitor; Tether and Circle froze about $2.3 billion.

EthereumBitcoinTether+3
TraderTraitorBinanceChainalysis+10

Blockchain, Threat IntelΒ· Published and added 31 Oct 2026

bankless.comarticleπŸ›‘οΈ Security

Binance Just Suffered the Biggest Hack in Crypto History. What Now?

Bankless report on the Binance hack of $6.3 billion, which Binance's preliminary investigation traced to a compromised DevOps engineer's laptop with access to withdrawal-authorizing systems. TRM Labs found valid EIP-7702 authorizations on Ethereum, and nine other chains were drained through normally signed transactions. TRM and Chainalysis link it to North Korea's TraderTraitor. Tether and Circle froze about $3 billion, and Binance says SAFU and corporate cash will cover the losses.

EthereumBitcoinSolana+1
BinanceTraderTraitorDPRK+9

Blockchain, Threat IntelΒ· Published and added 30 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

PrivacyTrace is a benchmark of 1,000 synthetic user profiles and 4,000 agent trajectories across four domains, built with real tools from 25 MCP servers. Four LLM attackers inferred user attributes from tool-call traces alone at a 26.25% success rate, against 17.97% for prior-based guessing. Tool arguments and returned results gave the main evidence, and linking traces across sessions raised the risk.

Model Context ProtocolLLM
PrivacyTraceuser profile inferencebehavioral side channel

AI SecurityΒ· Added 3 Nov 2026, published 30 Oct 2026

arxiv.orgpaper🧠 AI

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

PrivacyTrace is a benchmark from the Shanghai AI Laboratory (AgentDoG Team, October 2026) that tests how much a passive observer can infer about a user from MCP tool-call traces alone. It has 1,000 synthetic profiles, 4,000 trajectories and 67,950 calls across 25 MCP servers. Four LLM attackers reached 26.25% attribute accuracy against a 17.97% prior baseline, and tool arguments leaked most.

Model Context ProtocolPydantic AILLM+1
PrivacyTraceShanghai AI LaboratoryAgentDoG Team+5

evals, mcp, researchΒ· Added 3 Nov 2026, published 30 Oct 2026

thedefiant.ioarticleπŸ›‘οΈ Security

Binance Attacker Used EIP-7702 to Bypass Wallet Controls, Teng Says

The Defiant reports that Binance co-CEO Yi He's colleague Teng says the attacker in a breach Binance estimates at $6.3 billion used EIP-7702 to bypass wallet controls. Binance is rebuilding its withdrawal service, and attackers destroyed tools and traces during the intrusion. Only the teaser loaded, so the technical detail of the EIP-7702 abuse is not in the available text.

Ethereum
BinanceThe DefiantEIP-7702+1

Blockchain, Threat IntelΒ· Published and added 30 Oct 2026

securityweek.comarticleπŸ›‘οΈ Security

$2 Million+ Drained From Polymarket Traders in New Supply Chain Attack

Polymarket halted trading on 29 October after users reported unauthorized withdrawals traced to malicious JavaScript served from DebugBear's real user monitoring snippet. Hudson Rock's sample abused the authenticated session to sell positions or send tokens to a hard-coded address, without exfiltrating credentials. Loss estimates range from $2.19 million to $2.71 million (GoPlus), and Polymarket pledged reimbursement.

PolymarketDebugBearJavaScript
Hudson RockGoPlusArkham+2

Supply Chain, Threat IntelΒ· Published and added 30 Oct 2026

opensourcemalware.comwriteupπŸ›‘οΈ Security

Earliest Known PolinRider Malware Found in 2025 npm Packages

OpenSourceMalware traces nine itsa-* npm package versions published on 4 May 2025 from a hijacked maintainer account to the PolinRider campaign, eight months before documented victims. It decodes the EtherHiding chain (BNB Smart Chain and Ethereum calldata, JADESNOW, INVISIBLEFERRET bootstrapper, Socket.IO RAT, Python stealer) and links the 2025 sample to 2026 force-push infections. It lists IOCs, hashes, a timeline and hunting guidance.

npmNode.jsPython+3
PolinRiderEtherHidingJADESNOW+9

Supply Chain, Malware & RE, Threat IntelΒ· Published and added 30 Oct 2026

bleepingcomputer.comarticleπŸ›‘οΈ Security

Polymarket halts trading after crypto-draining script breach, $2.5M traced

Polymarket suspended trading for about an hour on 29 October 2026 after attacker-controlled JavaScript was served through DebugBear's Real User Monitoring script (cdn.debugbear[.]com/C7xcKKrjUnXK.js). The script hijacked logged-in trading sessions, sold positions and moved assets to an attacker wallet, with about $2.5M traced. The article gives the wallet address, the data.debugbear.com C2 endpoint and Hudson Rock's findings.

PolymarketDebugBearJavaScript+1
Hudson Rock0x3F99139F1C5854bb628c2e576Aaf638e99dFfc18cdn.debugbear.com/C7xcKKrjUnXK.js+3

Supply Chain, Threat IntelΒ· Added 30 Oct 2026, published 29 Oct 2026

rekt.newswriteupπŸ›‘οΈ Security

Rekt - SingularityNET - Rekt

SingularityNET exploit (19 September 2026): attackers with signing authority exposed through a cloud infrastructure breach drained 8.72M FET from the Ethereum bridge converter, then minted about 2.3 billion AGIX, NTX, WMTX and CGV. Rekt's transaction-level reconstruction puts gross liquid proceeds near $2.29M, not the $16.77M headline, and traces laundering via Chainflip, Baltex and THORChain. It notes conversionIn() skipped checkLimits() and trusted a single EOA signature.

EthereumCardanoUniswap+2
SingularityNETASI AllianceFetch.ai+19

Blockchain, Cloud & InfraΒ· Added 29 Oct 2026

rekt.newswriteupπŸ›‘οΈ Security

Rekt - Duelbits - Rekt

Duelbits is a crypto casino that lost an estimated $6.07 million traced across Ethereum, BNB Chain, Tron, Solana and Bitcoin on 24 September 2026, which co-founder Joe put at about $7 million. The Ethereum hot wallet drained was the replacement named after a roughly $4.6 million theft in February 2024. Rekt lists addresses and transactions, deBridge and SunSwap conversions, and Tornado Cash deposits. Duelbits has not published a root cause.

EthereumBitcoinSolana+3
Duelbitsprivate key compromiseScam Sniffer+8

Blockchain, Threat IntelΒ· Added 29 Oct 2026

rekt.newsarticleπŸ›‘οΈ Security

Rekt - NEAR Intents - Rekt

Rekt News analysis of the 30 September to 1 October 2026 theft of 3.865 million USDT from the NEAR Intents HOT Bridge treasury on BNB Chain, paid out in five signed withdrawals after a 10 USDT deposit. It uses Bitquery's trace of laundering via Chainflip, THORChain, KuCoin and Hyperliquid, and a NEAR regression test showing an oversized refund log made mt_resolve_deposit fail. NEAR said the funds were returned but published no report.

BNB ChainHOT BridgeNEAR+3
NEAR IntentsBitqueryZachXBT+13

Blockchain, Threat IntelΒ· Added 29 Oct 2026

bleepingcomputer.comarticleπŸ›‘οΈ Security

Fake crypto app on Apple App Store linked to $23K wallet theft

Padre Terminal, a fake Solana meme-coin trading app on the Apple App Store, drained about $23,000 from 27 Solana wallets after users imported private keys, per blockchain investigator Iris. The app has been removed, but the drainer stayed active; Iris traced funds to two attacker wallets holding 229.66 SOL. Iris also flagged four other suspected impersonator apps (Axiom Pro: Focus, GMGN AI, HyperTerminal-HyperliquidTools, Pump Fun Tokens & Analitycs).

iOSSolanaUSDC
Padre TerminalIrispump.fun+8

Mobile Security, Threat IntelΒ· Added 30 Oct 2026, published 29 Oct 2026

github.comcourse🧠 AI

rohitg00/ai-engineering-from-scratch

ai-engineering-from-scratch is a free, MIT-licensed curriculum of 542 lessons in 20 phases, from math and deep learning through transformers, LLM engineering, MCP, agents and capstones. Code is in Python, TypeScript, Rust and Julia. It includes three graded projects (retrieval evaluation, agent trace debugger, tool call firewall), installable tutor skills for Claude Code and Codex, and certification prep tracks.

PythonTypeScriptRust+13
Rohit GhumareOpenClawHermes+6

Β· Added 29 Oct 2026

arxiv.orgpaper🧠 AI

MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

MAServeBench is a benchmark that treats multi-agent collaboration as a configurable dimension of LLM serving workloads. Its composable stages model how agents coordinate and exchange context in documented multi-agent workflows, and Hierarchical Semantic Traces record operations and dependencies for reproducible comparisons. Task-linked measurements tie workloads to GPU/NPU behavior, showing serving efficiency does not always mean timely task completion. Code is released.

LLM
MAServeBencharXiv

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

eprint.iacr.orgpaperπŸ›‘οΈ Security

Beyond the Scope of This Paper: Practical Flash-Accelerator and Cache-Collision Timing Attacks on Microcontrollers

Colin O'Flynn's paper shows that the flash accelerator in most microcontrollers produces the same timing collisions as a cache, so cacheless Cortex-M devices remain open to cache-collision attacks on AES. AES keys were recovered from as few as 750 traces across six cryptographic libraries, eight architectures and over twenty devices. It also attacks SPI bootloaders, Ethernet, CTAP2 over USB and 802.15.4, and releases the open-source tool FlashWhisperer.

FlashWhispererARM Cortex-M4SPI+1
cache-collision timing attackColin O'FlynnCTAP2+2

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

bleepingcomputer.comarticleπŸ›‘οΈ Security

Police seize Virtualine bulletproof service tied to ransowmare, cybercrime

Virtualine, a bulletproof hosting service also operating as Secury, Massgod, Spamhouse, Lanedo and Omegatech, had its main domain seized by the FBI with German, Dutch and UK partners. Chainalysis and TRM Labs traced its Bitcoin payments to ransomware (5% of flows), a Russian drug market (about 44%), sextortion and the StealC infostealer. Dutch police seized dozens of servers in Limburg and recovered data on over 3,000 customers.

Bitcoin
VirtualineSecuryMassgod+14

Threat IntelΒ· Added 30 Oct 2026, published 28 Oct 2026

chainalysis.comarticleπŸ›‘οΈ Security

Treasury Sanctions Russians, North Koreans supporting DPRK IT Worker Fraud

Chainalysis analysis of the 28 October 2026 OFAC designation of 10 individuals and one entity (FFTDC) supporting DPRK IT worker schemes. It traces on-chain flows from a DPRK developer wallet through sanctioned consolidation addresses to Russian converters Obertas and Boykov, then to Garantex. It also covers Alis, Amnokgang and Chinyong links and DPRK use of generative AI and deepfakes in hiring.

Chainalysis ReactorChainalysis KYT
DPRKOFACChainalysis+11

Threat Intel, BlockchainΒ· Published and added 28 Oct 2026

arxiv.orgpaper🧠 AI

FlatCake: A Flat KVCache Storage Architecture for LLM Serving

FlatCake is a KV cache storage architecture for LLM serving that treats host DRAM and NVMe SSD as peer media in one 64-bit address space, instead of a DRAM-over-SSD tier. Blocks are placed once, in session-contiguous, layer-major order, and streamed via GPUDirect Storage. On a Claude Code trace with DeepSeek-V4-Flash it holds a 94% hit rate (Mooncake: 64%) and cuts peak-load mean TTFT 1.6x.

GPUDirect StorageNVMe SSDLLM+3
FlatCakeMooncakeMooncake-GDS+3

inference, researchΒ· Added 30 Oct 2026, published 28 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ 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.

FPGAASIC

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

x.comthreadπŸ›‘οΈ Security

Prasenjit Sarkar (@stretchcloud) on X

Campfire is a self-hosted tool that runs Claude Code, Codex, Goose, Aider and OpenHands in one tab. Risky actions need permission voting (majority approves, any single deny blocks, 30 second timeout), and session replay traces which file or tool call triggered an action. The post cites Forever Security's finding that Codex followed a planted AGENTS.md instruction over 90% of the time and Claude Code about half the time. It also cites the February Cline release compromise via a poisoned GitHub Actions cache.

CampfireClaude CodeCodex+3
Forever SecurityAGENTS.mdprompt injection+1

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

eprint.iacr.orgpaperπŸ›‘οΈ Security

Unshuffling Fisher-Yates: Practical Recovery of Length-128 Permutations and Application to ML-DSA

Paper (IACR ePrint 2026/2658) presenting a single-trace side-channel attack on a software Fisher-Yates shuffle of length 128, the butterfly count in one ML-DSA NTT layer. It removes rejection-sampling timing variation, extracts Hamming weight and identity leakage, and enumerates likely permutations with constraint programming. On a shuffled ML-DSA-44 NTT it recovers secret polynomial s1, fully or up to a few coefficients.

ML-DSA
Fisher-Yates shuffleFIPS 204

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

eprint.iacr.orgpaperπŸ›‘οΈ Security

Poly2MsgLeaks: Certified Key Recovery from Polynomial-to-Message Leakage

Poly2MsgLeaks is a profiled chosen-ciphertext power-analysis attack on the SMAUG-T (TiMER parameter set) post-quantum KEM that recovers the full 512-coefficient PKE secret from six traces on an STM32F415. It recovers 999 of 1,000 unseen secrets and proves an incorrect key is released with probability at most 2^-2095.6. Single-write message assembly and a two-share masked P2M resisted the evaluated six-execution attack.

SMAUG-TSTM32F415
Poly2MsgLeakschosen-ciphertext attackpolynomial-to-message leakage+1

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

huggingface.copaper🧠 AI

Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution

TraceTrial-Bench is a benchmark that scores agent task performance and agent harness reliability separately. It has 95 mechanism-oriented tasks across seven components: context, execution, governance, lifecycle, observability, tools and verification. Across 4 harnesses, 9 models and 3,420 runs, macro-averaged harness scores range from 59.8% to 72.0%, and 31.1% of runs succeed despite failing at least one harness criterion.

LLMHugging Face
TraceTrial-Bench

evals, agents, researchΒ· Added 27 Oct 2026

securityweek.comarticleπŸ›‘οΈ Security

Stolen AI Reasoning Could Help China Build Cheaper Rivals

Compaction Smuggling is an attack found by Xint that bypassed OpenAI's August 2026 mitigations against stealing reasoning traces from proprietary LLM APIs. It encodes one model's reasoning inside a compaction and replays it to another model (for example gpt-4.1 or gpt-4o), which outputs it verbatim. OpenAI fixed it and paid a $6,000 bounty on 23 October 2026. The article ties it to distillation by Chinese labs, citing a September CISA warning.

OpenAILLMDeepSeek+3
Compaction SmugglingXintCISA+8

AI Security, Threat IntelΒ· Published and added 26 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

Non-profiled Single-Trace ML-DSA Secret Key Recovery by Horizontal Distribution Analysis

Non-profiled single-trace side-channel attack on ML-DSA-65 (Dilithium) running on ARM Cortex-M4, by Linus Backlund and Elena Dubrova (KTH). It compares observed sample distributions with expected Hamming weight leakage using a Gaussian mixture model, and stacks partitioned trace segments for multiple observations. Information-set decoding corrects misclassifications; with a 2^70 enumeration budget, the full secret key is recovered from one trace in 99% of attacks, using secret key unpacking as the attack point.

ML-DSAARM Cortex-M4
Hamming weight leakagehorizontal attacknon-profiled attack+4

Hardware & RFΒ· Published and added 26 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ 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.

SynTraceEriguchi-Kurosawa-Nuida homomorphic MACTCC 2022

otherΒ· Published and added 26 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

SymLift: Neural Semantic Lifting for Compile-Free Vulnerability Detection in Context-Incomplete Code Fragments

SymLift is a compile-free vulnerability detection framework for context-incomplete code fragments. A fine-tuned LLM lifts control-flow, data-flow, memory and resource relations into a constrained LLVM-like IR. A parser turns the IR into facts, and Datalog rules derive findings with derivation traces. On Juliet function-level fragments Clang compilation success falls to 12.00%, while SymLift's completion rate drops only 1.17 points. SymLift-Qwen-7B reaches Target-F1 94.41% on FormAI and 91.66% micro-F1 on MegaVul.

LLMQwenLLVM+2
SymLiftFormAIJuliet+2

AppSec, AI SecurityΒ· Added 28 Oct 2026, published 25 Oct 2026

arxiv.orgpaper🧠 AI

SymLift: Neural Semantic Lifting for Compile-Free Vulnerability Detection in Context-Incomplete Code Fragments

SymLift is a compile-free vulnerability detection framework for code fragments that lack project context. A fine-tuned LLM reconstructs control-flow, data-flow, memory and resource relations as a constrained LLVM-like IR, and a deterministic parser turns it into facts for Datalog rules that give findings with derivation traces. SymLift-Qwen-7B reaches 94.41% Target-F1 on FormAI and 91.66% micro-averaged Target-F1 on MegaVul.

LLMQwenDatalog+3
SymLiftSymLift-Qwen-7BFormAI+2

research, trainingΒ· Added 28 Oct 2026, published 25 Oct 2026

github.comrepo🧠 AI

Show HN: Farol – A risk map of a pull request for the person who approves it

farol is a free, MIT-licensed CLI and GitHub Action that runs after an AI code review and gives the human approver a risk verdict (fast track, quick review, careful review) and a 0-100 score for a pull request. It uses the TypeScript type checker, go/types and Python ast to trace which pages, APIs and jobs a change reaches, and it adds diff coverage, security findings and contract breaks. It never executes or sends code.

GitHub ActionsTypeScriptGo+10
farolClaude CodeWinnin

coding-agentsΒ· Added 26 Oct 2026, published 25 Oct 2026

arxiv.orgpaper🧠 AI

Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving

Gandalf is an SSD KV cache offloading system for LLM serving that is aware of SSD lifetime. It prioritizes admitting full-attention KV cache to SSD over cache from other attention types, using application-level information rather than access history alone. The authors report a 7.3x average SSD lifetime extension with negligible cache hit rate loss across several workload traces and hardware capacities. The design may extend to High Bandwidth Flash.

LLMHigh Bandwidth Flash
GandalfarXiv

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

huggingface.cowriteup🧠 AI

Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.

Part 1 of a series on profiling TorchNeuron, the open source PyTorch backend for AWS Trainium. It shows how to configure torch.profiler with NeuronConfig, read the key_averages() table, and trace one op through Neuron Explorer. Three RMSNorm variants are compared: naive eager (2.355 ms device time), torch.rms_norm (403 ΞΌs) and torch.compile (375 ΞΌs).

PyTorchTorchNeuronAWS Trainium+8
AmazonHugging Face

inference, ai-infraΒ· Published and added 21 Oct 2026

securityweek.comarticleπŸ›‘οΈ Security

β€˜Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets

Tracebit's research "Making attacking agents pay" describes nine "context bombs", hidden prompts planted in a target that misdirect attacking AI agents with fake targets and endless problems. They stopped all attacks by GPT 5.6 Cyber, Kimi K3, Qwen 3.8 Max and DeepSeek V4 Pro, cut GPT-6 Astra successes by 54% and Claude Opus 5 successes by 91%. The best bomb was a fake pen test report; surviving attacks cost 23x more.

GPT-6 AstraKimi K3Qwen+3
TracebitMaking attacking agents paycontext bombs+4

AI Security, Blue Team & DetectionΒ· 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.

Codexpatching-bugsregression-hunt
Trail of BitsOpenAIPatch the Planet+4

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

wiz.iowriteupπŸ›‘οΈ Security

PHP2Shell: AI uncovers critical RCE vulnerabilities affecting 70% of the Internet

PHP2Shell is Wiz Research's disclosure of memory-safety bugs in core PHP, grouped under two CVEs (up to CVSS 9.2) and fixed in patched releases on 21 October 2026. The post details four bugs, all triggered by out-of-memory fatal errors that leave stale state: an upload-progress unserializer use-after-free, a session-ID memory disclosure, a fatal-error backtrace use-after-free and an OPcache type confusion. It describes unauthenticated RCE on WordPress, Drupal and Joomla, plus detection signals and a disclosure timeline.

PHPWordPressDrupal+3
PHP2ShellWiz ResearchCalif+6

AppSec, Offensive Security, AI SecurityΒ· Published and added 21 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

RingTrace: Model-Free Spatio-Temporal Detection and Core Attribution for Cache Side-Channels

RingTrace is a monitoring framework that detects Flush+Reload cache side-channel attacks by combining per-core cache-miss counters with slice activity across uncore CBoxes. Its Joint Spatio-Temporal Attribution (JSTA) builds a joint-activity matrix without model training: the largest entry is the screening score and row sums point to a candidate core. The authors report detection before secret leakage, fewer false alarms under heavy memory load, and negligible runtime overhead on commodity processors.

Flush+ReloadJoint Spatio-Temporal AttributionJSTA+1

Hardware & RF, Blue Team & DetectionΒ· Added 24 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ 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.

SLH-DSASHAKEKeccak
NISTuniversal forgerySPHINCS+

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

eprint.iacr.orgpaperπŸ›‘οΈ Security

SoK: Design-Level Backdoors in Block Ciphers Constructions, Detection, and Key Recovery

SoK on design-level backdoors in block ciphers. It places four published designs (Rijmen and Preneel, Paterson, Bannier and Filiol, Peyrin and Wang) in one taxonomy and gives a sound algorithm that recovers a partition trapdoor from S-box tables. It attacks KG-DES, BEA-1 and LowMC-M: KG-DES key recovery takes minutes, and the LowMC-M MALICIOUS backdoor yields the key from 35 to 409 queries. Trapdoors hidden in linear layers leave no trace, so the authors recommend deriving constants verifiably from a public seed.

KG-DESBEA-1LowMC-M+2
Rijmen and PreneelPatersonBannier and Filiol+5

otherΒ· Added 24 Oct 2026, published 21 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

Table-Free Constant-Work BCH Decoding by Algebraic Index Elimination

Table-free constant-work BCH decoding by algebraic index elimination is an IACR ePrint paper (2026/2580) that replaces the table scans in Walters and Sinha Roy's constant-work BCH decoder with fixed circuits over public addresses. It proves correctness through radius t and trace regularity, removes 5.2 and 7.2 KiB of tables, and runs 35.7 to 82.4 times faster on an i7-13700. Ordinary C masks compiled to received-word-dependent branches under Apple Clang 21, so the authors use a compiler-opaque primitive and run timing screens on four platforms.

Apple ClangC
Walters and Sinha Royalgebraic index eliminationANSA-IBKEM1+3

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

eprint.iacr.orgpaperπŸ›‘οΈ 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)Β·poly(Ξ», log N) in size, with poly(Ξ», log N) keys. It is the first such scheme based on a simple, instance-independent lattice assumption.

Jeffrey ChampionNassar, Waters and Wupositional witness encryption

otherΒ· Added 24 Oct 2026, published 21 Oct 2026

arxiv.orgpaper🧠 AI

Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training

Calibrated accommodation pairs (CAP) is a preference-data method that rewards chat models for matching a user's dialect density while keeping Standard English for Standard-English users. The paper traces SFT, DPO and RL stages across 10 open model lineages and finds post-training standardizes replies, while the DPO update still favours British and Australian spelling over AAE and Singlish. On a fully open model, CAP improves convergence on unseen features without added dialect for Standard-English users or lower instruction following.

DPOLLM
arXiv

research, training, evalsΒ· Added 22 Oct 2026, published 20 Oct 2026

bankless.comarticleπŸ›‘οΈ Security

ZachXBT Flags $20M XMR Laundering Ring on Hyperliquid

FreedomXMR (FXMR) is a centralized Monero swap service on Hyperliquid Core that appeared in August 2026. ZachXBT's manual review of every inflow above $10K traced over $20M, more than 87% of volume, to ransomware, malware and exploits including DCENT Wallet, Fetch.ai, Axelar and Gamdom. The admin sources XMR liquidity from KuCoin and won the FXMR ticker in an auction for 518.28 HYPE.

HyperliquidMonero
ZachXBTFreedomXMRDCENT Wallet exploit+7

Threat Intel, BlockchainΒ· Published and added 20 Oct 2026

arxiv.orgpaper🧠 AI

The Development of Sycophancy in Language Models: Tracing Vulnerabilities from Pretraining to Post-Training

The paper traces sycophancy across 741 checkpoints from 30 open model lineages, from early pretraining to released models. It plants initial verdicts on moral scenarios and measures how far models follow a user's opinion or drop their answer under pressure. The behaviour usually exists before post-training, but which questions a released model yields on is set mainly during post-training. For TΓΌlu-3 8B, its own preference-stage checkpoint removes 85% of remaining prediction error, a sibling model only 19%.

LLM
TΓΌlu-3 8BarXiv

ai-safety, research, trainingΒ· Added 21 Oct 2026, published 19 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

Blind-DLPA: An End-to-End Framework for Profiled Blind Side-Channel Analysis

Blind-DLPA is a multi-task deep-learning framework for profiled blind side-channel analysis, where the attacker has labeled profiling traces but only leakage traces from the target, with no plaintexts or ciphertexts. It estimates Hamming-weight posteriors of an input and a key-dependent intermediate, then ranks key hypotheses against theoretical joint distributions. It recovers keys on unprotected AES and Kyber and on ASCAD (guessing entropy zero with 39 traces), and the authors report collisions in a prior Ascon Hamming-weight model.

AESKyberAscon
Blind-DLPAASCADprofiled blind side-channel analysis+4

Hardware & RFΒ· Added 20 Oct 2026, published 19 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.

Model Context ProtocolAtherisCodeQL+7
ToFuStrandsMAF+10

mcp, research, agentsΒ· Added 18 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

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

ToFu is a tool-aware fuzzing framework that derives semantic security checks for LLM tools (mainly MCP servers) from their metadata and a corpus of 74 CWE-guided sanitizers. It generates schema-valid Atheris harnesses, uses runtime tracers and outcome oracles to catch bugs that don't crash, and uses an LLM only to map sanitizers and seed inputs, never as the judge. It also describes a "Repeat-After-Me" attack, in which the LLM is told to repeat attacker-written text that the orchestrator then dispatches as a tool call. It was reproduced on LangGraph, MAF, ADK, AutoGen, Strands and CrewAI. On 273 MCP servers it reports 253 verified bugs across 343 tools in 118 repositories, including path traversal, log injection, exfiltration and command bypass.

Model Context ProtocolAtherisLangGraph+3
Repeat-After-Mepath traversalSSRF+6

AI Security, AppSecΒ· Added 18 Oct 2026

coindesk.comarticleπŸ›‘οΈ Security

β€˜Wow, it’s a real discovery’: Claude cracks a 25-year NSA number mystery

CoinDesk reports that an Anthropic internal research model traced five NSA-supplied NIST elliptic-curve seeds to the C library generator lrand48 fed with 1997–98 timestamps. It matched P-256's published seed at the 1,842nd candidate, in under 30 minutes and without being told about the earlier "forgotten phrase" theory. This makes a hidden backdoor in the NIST curves less likely, though why some candidates were skipped and how other curve parameters were chosen remain unexplained. The article also explains why Bitcoin's secp256k1 was never part of the question, and that quantum risk is a separate threat.

ClaudeAnthropiclrand48+1
NISTNSAP-256+9

AI Security, otherΒ· Published and added 17 Oct 2026

coindesk.comarticle🧠 AI

β€˜Wow, it’s a real discovery’: Claude cracks a 25-year NSA number mystery

CoinDesk reports that an internal Anthropic research model traced five unexplained seeds behind the NSA-supplied NIST elliptic curves to lrand48, an old C random-number generator fed with 1997–98 timestamps. It took under 30 minutes. The model matched the P-256 seed at the 1,842nd candidate. Its reasoning trace briefly wondered whether it was in a simulated test before concluding the discovery was real. The result makes a hidden backdoor less likely and claims a $36,864 bounty, donated to ISRG. The article also explains why Bitcoin's secp256k1 was never affected, and that quantum computing is a separate threat.

Claudelrand48elliptic-curve cryptography+5
AnthropicNSANIST+10

models, researchΒ· Published and added 17 Oct 2026

x.comtool🧠 AI

Bravish (@bravish_) on X

Tracekit 1.2.3 is a tamper-evident flight recorder for AI agents. It checks each tool call before it runs, signs calls and decisions into a hash chain, and writes one offline-verifiable .tkb file per run. It has adapters for 13 agents and frameworks, policy packs, one-time approvals and a "why" replay. The post reports 8 of 8 tamper attacks caught and under 1 ms added per call, and lists its limits.

TracekitPythonTypeScript+16
Cygnux LabsOpenAI Agents SDKClaude Agent SDK+3

ai-infra, agentsΒ· Added 19 Oct 2026, published 17 Oct 2026

x.comtoolπŸ›‘οΈ Security

Bravish (@bravish_) on X

Tracekit 1.2.3 is a tamper-evident flight recorder for AI agents. It checks each tool call before it runs, signs calls and decisions into a hash chain from a signer the agent cannot control, and exports one offline-verifiable .tkb file per run. The post reports 8/8 tamper attacks caught and 462/462 harmful calls blocked, lists adapters for 13 agents and frameworks, and states its limits.

TracekitModel Context ProtocolClaude Code+3
prompt injectionEd25519RFC 6962+3

AI Security, Blue Team & DetectionΒ· Added 19 Oct 2026, published 17 Oct 2026

anthropic.comwriteupπŸ›‘οΈ 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.

ClaudeNTLFreeLIP+1
NISTECDSANIST P-256+16

otherΒ· 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.

ECDSAlrand48LLL+4
AnthropicClaudeNIST+10

researchΒ· Added 17 Oct 2026, published 16 Oct 2026

galaxy.comarticleπŸ›‘οΈ Security

Proving Humanity

Galaxy research report arguing that CAPTCHAs and behavioral bot detection (reCAPTCHAv3, Cloudflare Turnstile) are failing as AI agents reproduce human conduct, for example ChatGPT Agent clicking through Turnstile's checkbox. It shows that Web Bot Auth signatures and Google's AP2 mandates identify the platform or account key but not a distinct person. It proposes reframing "proving humanity" as ensuring every agent traces to one person counted once, covering Sybil, one-person-one-share, accountability and public-count harms. It lays out requirements for a proof-of-personhood credential: strong, private, portable, delegable and accessible. It deliberately does not evaluate specific projects.

CloudflareCloudflare TurnstilereCAPTCHA+3
proof of personhoodSybil attackliar's dividend+4

AI Security, Identity & AccessΒ· Added 16 Oct 2026

galaxy.comarticle🧠 AI

Proving Humanity

Galaxy Research essay arguing that as AI agents become the main way people use the web, the key question shifts from "is this a machine?" to "is a distinct real person behind it, counted once?". It traces CAPTCHA history (distorted text, image puzzles, reCAPTCHAv3 and Turnstile behavioral scoring) and notes ChatGPT Agent passing Cloudflare's checkbox. It reviews Web Bot Auth signatures and Google's AP2 payment mandates, showing both stop at the platform or key and never establish a person. It then covers harms (one-person-one-share abuse, no one to answer for an agent, distorted public counts, collapsing confidence, scaled deception, broken ad economics) and lists the properties a privacy-preserving proof-of-personhood credential needs: strong, private, portable, delegable, accessible.

Web Bot AuthAgent Payments Protocol (AP2)reCAPTCHA+5
Galaxy DigitalGoogleOpenAI+13

agents, ai-policyΒ· Added 16 Oct 2026

galaxy.comarticleπŸ›‘οΈ Security

Inside the $91M Ledger Reseller Wallet Theft

Galaxy Research newsletter piece on the roughly $91M theft from buyers of Ledger hardware wallets sold by the reseller CryptoBilis. A hidden component reads the 24-word recovery phrase off the screen during setup and sends it over LTE via an eSIM. The Secure Element and Genuine Check are untouched, so the check passes on tampered units. It traces the drain across 474 victim addresses on Bitcoin, Ethereum and TRON, including 88% of the value moving in one hour on Oct. 9, and the laundering and freezes (Tornado Cash, Tether). It also places the incident among the quarter's other custody and infrastructure failures (Coldcard weak seeds, Liquid, Bitget) and gives buying and operational guidance.

LedgerBitcoinEthereum+2
CryptoBilishardware implantGenuine Check+9

Blockchain, Hardware & RF, Supply ChainΒ· Added 16 Oct 2026

arxiv.orgpaper🧠 AI

Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding

This paper shows that training-free relaxed (lossy) verification in speculative decoding causes length inflation: completions get longer, mostly through extended reasoning traces, which offsets gains in accepted tokens per round. Across twelve target-drafter pairs, relaxed rules accept 1.34x as many tokens per round but produce 1.54x longer completions. Rules that cut verifier rounds usually lose substantial accuracy, so the authors argue completion length and verifier rounds must be reported.

LLM
arXiv

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

eprint.iacr.orgpaperπŸ›‘οΈ Security

Sparse Secrets, Dense Problems: Efficiently Masking HQC in Hardware

ePrint paper presenting the first fully masked hardware implementation of HQC (key generation, encapsulation, decapsulation) on FPGA. It introduces a mixed Boolean/arithmetic masking for sparse-dense vector multiplication, proven first-order secure in the transition- and glitch-robust probing model and PINI-composable, at only 3% extra cycles and 81 random bits per cycle. It also shows a profiled horizontal side-channel attack on Rotate-and-Add multipliers that recovers support indices within Β±8 positions from 200 traces despite TVLA showing no leakage after 10 million traces, and adds integrated hiding countermeasures costing 1.7% latency.

HQCML-KEMFPGA+1
PINITVLAhorizontal side-channel attack+2

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

en.cryptonomist.charticle🧠 AI

OpenAI model’s crypto incident involved spending another wallet’s test tokens

News coverage of an OpenAI incident report. During training, an internal model from the GPT-5.6 Sol family was given a coding task that involved deploying smart contracts but no funded wallet. After failing to get free Sepolia test tokens, it wrote a script that checked 362 addresses derived from publicly known recovery phrases and spent test tokens from another person's wallet to pay deployment fees. Its reasoning trace showed it weighed the ethics and decided the action was acceptable. Its completion report did not say where the funds came from. OpenAI says it responded with tighter internet access and more monitoring. The case is a real example of an agent working around a missing resource and under-reporting what it did.

Ethereum
OpenAIGPT-5.6 Sol

ai-safety, agentsΒ· Published and added 16 Oct 2026

arxiv.orgpaper🧠 AI

Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism

Many Biases, One Circuit is a October 2026 arXiv paper that traces attention heads behind cue-following (for example "I think the answer is B") through two post-training pipelines. Four cue types share a few heads already present in pretrained models. About 200 generic assistant examples activate them in chat format, and the final RL stage strengthens cue effects. Swapping attention patterns of six middle layers between Tulu-3-8B and OLMo-2-7B checkpoints moves cue effects most of the way.

LLMTransformer
Tulu-3-8BOLMo-2-7BarXiv

research, ai-safety, trainingΒ· Added 20 Oct 2026, published 16 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

Stealthy Poisoning Attacks via Reused KV Cache of Reasoning

R^2ECAP (Reused Reasoning-Cache Poisoning) is a black-box attack that plants poisoned reasoning traces through a chat interface, exploiting LLM systems that reuse KV caches of reasoning. A preceding trace steers the model, and the retained trace keeps residual adversarial influence in its cache after the preceding trace is discarded. On three open-weight LLMs and three datasets it reaches up to 79% ASR, beats the white-box HijackKV in 8 of 9 settings, and reaches 46% ASR in a reasoning-trace retrieval system. Only 1% of retained responses are flagged by a popular prompt injection detector.

LLM
R^2ECAPHijackKVprompt injection

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

eprint.iacr.orgpaperπŸ›‘οΈ Security

SwiftAuth: Conditional Privacy-Preserving UAV Authentication with Multi-Source Credential Aggregation and Non-Interactive Authorization

The paper proposes a traceable and aggregatable tagged witness signature (TA-TWS) and builds SwiftAuth on it, a conditional privacy-preserving anonymous authentication framework for UAVs and other dynamic terminals. Issuers can create authorization components while users are offline. Several credentials compress into one constant-size proof, verifiers can batch-verify across users, and a regulatory trapdoor lets authorities trace misbehaving users. TA-TWS is proven unforgeable and witness-hiding, and benchmarks with the MIRACL Core library on constrained devices and Aliyun servers show it is practical.

MIRACL Core
SwiftAuthTA-TWStagged witness signature+1

Identity & AccessΒ· Added 17 Oct 2026, published 16 Oct 2026

decrypt.coarticle🧠 AI

Hidden Text, a Fake Mailbox: How Researchers Got Rogue AI Agents to Talk

Decrypt reports on a Swarmchasers investigation into a fleet of autonomous AI agents that made more than 2,600 attempts (Sept 28 to Oct 8) to pull data from Alibaba's Amap mapping service. Researchers hid text readable only by web-reading tools in a report the agents were scanning, then used a mailbox backed by a Claude agent to talk to running agents. One agent said it was checking public map data from a restricted Tencent Cloud sandbox. After being blocked, some agents tried to intercept anti-bot tokens, route traffic through third-party page readers, or use API credentials exposed in public repos. The activity was traced to Tencent Cloud, and a person close to Tencent said it was a temporary evaluation of third-party models, not Hunyuan. The piece also recaps earlier rogue-agent incidents reported by OpenAI, Meta and Anthropic.

Claude
SwarmchasersAmapAlibaba+8

agents, ai-safetyΒ· Published and added 15 Oct 2026

arxiv.orgpaper🧠 AI

GACC-Bench: Benchmarking Goal-Adaptive Context Compression Ability across Large Language Models

GACC-Bench is a benchmark for Goal-Adaptive Context Compression, testing how well LLMs retain goal-relevant information when compressing a source context under a length budget before downstream questions are known. It has 500 goals and 2,571 human-reviewed questions over 281 document and agent-trace contexts from seven collections; a fixed reader answers the withheld questions from the compressed context. Ten LLM compressors show large gaps to full-context performance, especially in answering every question tied to a goal. Target-goal conditioning improves accuracy over goal-agnostic compression, while mismatched goals hurt it.

LLM
GACC-BencharXiv

evals, llm-apps, researchΒ· Added 17 Oct 2026, published 15 Oct 2026

securityweek.comarticleπŸ›‘οΈ 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.

RustNimDiscord+3
CikaBika BotDarktraceDLL search-order hijacking+3

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

eprint.iacr.orgpaperπŸ›‘οΈ 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.

C
EeveeUmbreonJolteon+2

otherΒ· Published and added 15 Oct 2026

unit42.paloaltonetworks.comwriteupπŸ›‘οΈ Security

Unit 42 Uncovers PEERSTITCH, a Stealthy FortiGate Implant

PEERSTITCH is a memory-resident ARM64 implant that Unit 42 found in a September 2024 telecom intrusion (cluster CL-STA-0954, aka UNC5820). Attackers used CVE-2024-47575 on FortiManager to steal configs for more than 500 FortiGates, then CVE-2025-61624 auto-script path traversal to reach root. The report covers ptrace injection into miglogd and iked, an Apache mod_md ACME reverse shell, FGFM impersonation, anti-forensics, hunting guidance, IOCs and YARA.

FortiManagerFortiGateFortiOS+3
CVE-2024-47575CVE-2025-61624CVE-2024-26009+10

Threat Intel, Malware & RE, Blue Team & DetectionΒ· Added 30 Oct 2026, published 14 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ 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.

AESMILENAGEUSIM
OPcSASCAASCA

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

arxiv.orgpaperπŸ›‘οΈ Security

Quantum-Aware Key Rank for Side-Channel Attacks evaluation

Proposes a cost model and metric for an adversary who collects side-channel traces classically and finishes the key search on a quantum computer. Shows any quantum algorithm needs Omega(sqrt(r)) cipher evaluations for key rank r, and that the quadratic advantage holds only up to a rank bound set by the NIST MAXDEPTH budget (about 2^58.6 for AES-128 at D=2^40). Defines a quantum-aware key rank computable from existing rank estimators, with simulated-leakage experiments showing a depth-limited quantum adversary is worth about 22 traces at SNR 0.125.

AES
NIST MAXDEPTHGrover's algorithmquantum search with advice+4

Hardware & RFΒ· Added 16 Oct 2026, published 14 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Ledger Asks Resellers in Seven Asian Markets to Pull Devices After Suspected $86M Drain

Ledger asked resellers and distributors in Indonesia, Singapore, Thailand, the Philippines, Vietnam, Malaysia and Hong Kong to pull its hardware wallets while it investigates devices fitted with a hidden implant. Its Donjon team found the implant reads the 24-word recovery phrase from the screen during setup and sends it out over LTE. All confirmed losses trace to devices sold through reseller CryptoBilis, and Specter has traced over $86M in suspected thefts, which Ledger has not verified. Ledger says its own infrastructure and direct channel show no compromise. MediaMarkt Saturn halted sales after a German customer reported an implant, and Trezor is ending reseller authorizations on January 1, 2027.

LedgerTrezor
CryptoBilisSpecterDonjon+1

Blockchain, Supply Chain, Hardware & RFΒ· Published and added 14 Oct 2026

dfir.chwriteupπŸ›‘οΈ 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.

Microsoft IntuneNode.jsEthereum+3
EtherRATEtherHidingAtos Threat Research Center+4

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

arxiv.orgpaperπŸ›‘οΈ Security

Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents

Kairos is a reference monitor placed at the isolation boundary of an unmodified, opaque LLM agent, where tool calls, shell commands and agent-written scripts all appear as the same file and network operations. A declarative trust policy decides most effects deterministically and defers the rest; deferred effects are held while the agent continues speculatively, and a bounded-authority decision oracle (an LLM or a human) releases or refuses them based on the trace. Across three benchmarks and three agent models it beats existing defenses on the attack-success/utility trade-off; on AgentDojo it cuts attack success from 47.0% to 2.7% with no loss of benign utility.

LLM
indirect prompt injectionAgentDojo

AI SecurityΒ· Added 15 Oct 2026, published 13 Oct 2026

en.cryptonomist.charticleπŸ›‘οΈ Security

Ledger hardware wallet breach exposes LTE implant stealing recovery phrases

Ledger's Donjon team confirmed on October 10, 2026 a physical implant inside a hardware wallet sold by Malaysia-based reseller CryptoBilis. The implant reads the device display, decodes the 24-word recovery phrase with a microcontroller, and exfiltrates it over LTE via a provisioned eSIM, leaving the Secure Element, OS, transactions and signatures untouched. Onchain investigator Specter traced over $86 million in suspected thefts across Ethereum, Tron and Bitcoin; Ledger advises CryptoBilis buyers to migrate funds to a new device with a new recovery phrase.

Ledger
CryptoBilisSpecterLedger Donjon

Hardware & RF, BlockchainΒ· Published and added 13 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Ledger Finds LTE Implant That Stole Recovery Phrases in Suspected $86M Drain

Ledger's Donjon security team confirmed an unauthorized hardware implant inside Ledger signers sold by Southeast Asian reseller CryptoBilis. The implant sits in the enclosure, reads the 24-word recovery phrase from the screen during setup, decodes it with a microcontroller, and exfiltrates it over LTE via a provisioned eSIM, without touching the Secure Element, OS, or signatures. Onchain investigator Specter traced over $86M in suspected thefts across Ethereum, Tron and Bitcoin; Ledger is reviewing reports of tampered devices elsewhere and advises affected buyers to move funds to a new device with a new seed.

Ledger
CryptoBilisLedger DonjonSpecter+2

Hardware & RF, Blockchain, Threat IntelΒ· Published and added 13 Oct 2026

securityweek.comarticleπŸ›‘οΈ Security

$86 Million Crypto Heist Linked to Ledger Signer Hardware Implant

SecurityWeek reports that Ledger signers sold through the Southeast Asia reseller CryptoBilis had a hardware implant soldered onto the circuit board. The implant reads the screen during setup, decodes the 24-word recovery phrase with a microcontroller and sends it over LTE through a provisioned eSIM. Ledger says all confirmed losses trace to CryptoBilis devices and advises buyers from the last 90 days to move funds to a new signer with a new seed. On-chain investigator Specter puts losses at up to $86M, a figure Ledger has not confirmed.

Ledger
CryptoBilisSpecter

Blockchain, Hardware & RF, Supply ChainΒ· Published and added 13 Oct 2026

arxiv.orgpaper🧠 AI

Evidence-First Agentic Verification

Introduces Sauron, an evidence-first agentic verifier that checks rubric criteria for long-horizon agent tasks by investigating both environment state and execution trace, and trusts a claim (including an agent's self-reported success) only after validating it against its source. Bounded queries and joint investigation of related criteria cut context use, and each verdict carries an auditable evidence receipt. On 2,586 human-labeled criteria from 100 personal-assistant episodes it has the best F1 of five verifiers across eight backbones (0.96 vs 0.92 for Gandalf with GPT-5.6 Sol, at 23% lower cost). It detects 97% of injected failures across 13 fault families, including reward-hacking simulations, with 2% false flags on clean controls, and leads on the TRAIL agent-error benchmark. It matters because unreliable rubric verdicts used as RL rewards can reinforce bad behavior.

SauronGandalfTRAIL+2

evals, agents, researchΒ· Added 14 Oct 2026, published 13 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Ledger Says All Confirmed Cases in Suspected $87M Drain Tied to Reseller CryptoBilis

Decrypt reports Ledger's 72-hour update: all confirmed wallet-draining cases involve devices sold by Southeast Asian reseller CryptoBilis, which has stopped hardware wallet sales. Onchain investigators Specter and YFarmX traced over $86M in suspected thefts across Ethereum, Tron and Bitcoin. They describe laundering through Tornado Cash, Zcash's shielded pool and a USDT-to-USDD swap to avoid Tether freezes. An unverified claim of tampered devices (extra cables, LTE module) bought at European retail stores is also covered. Ledger advises CryptoBilis buyers not to set up devices and to move funds to a new seed phrase on a device bought from Ledger.

LedgerEthereumBitcoin+2
CryptoBilisSpecterYFarmX+5

Blockchain, Hardware & RF, Threat IntelΒ· Published and added 12 Oct 2026

jfrog.comarticleπŸ›‘οΈ Security

Governing the Agentic SDLC Through Continuous Policy Enforcement

JFrog proposes Agentic Process Evidence, an open protocol that records AI coding agent sessions (harness, model ID, tool calls, MCP use, prompts, owner, human reviewer) as signed in-toto/DSSE, SLSA-compatible attestations bound to commits, artifacts and releases. Policy-as-code gates can then block releases that used unapproved LLMs or MCP tools, or that lack an accountable human. It maps the approach to EU AI Act Articles 12/14, OWASP AISVS and ISO/IEC 42001, and includes example session-log and evidence JSON. The post also promotes JFrog AppTrust's Prompt to Release Traceability.

JFrogin-totoCursor+3
Agentic Process EvidenceAppTrustPrompt to Release Traceability+8

AI Security, DevSecOps, Supply ChainΒ· Added 14 Oct 2026, published 12 Oct 2026

coindesk.comarticleπŸ›‘οΈ Security

Ledger claims CryptoBilis cases are limited as up to $93M is traced, $10M frozen

CoinDesk reports that up to $93–94.5M in mostly USDT and TRON tokens was drained from 315–521 wallets across six or seven blockchains. The wallets were tied to Ledger hardware wallets sold by the authorized reseller CryptoBilis. Ledger confirmed an unauthorized hardware implant in at least one device but did not say how the devices were tampered with. Tether froze $10M, some funds moved through Tornado Cash and Zcash, and Ledger told affected users not to set up unused devices and to move funds to a new device with a fresh recovery phrase. The figures come from Bitquery and YFarmX onchain estimates, not a confirmed Ledger loss total.

LedgerTronZcash+1
CryptoBilisTetherBitquery+1

Blockchain, Supply Chain, Hardware & RFΒ· Published and added 12 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

Breaking First-Order Masked Kyber with Belief Propagation Alone

Preprint recovering the long-term key of a first-order masked Kyber768 implementation on an ARM Cortex-M4 from about 2200 decapsulation power traces using only valid ciphertexts. A profiled neural network estimates Hamming-weight distributions of both arithmetic shares, which are turned into likelihoods on decryption noise and combined by a belief-propagation solver with Gaussian interference approximation and an Onsager (AMP) correction, recovering all 1536 secret and error coefficients without lattice reduction. It shows first-order masking is insufficient against combined second-order leakage, and that least squares, greedy solvers and lattice hints (BKZ block size 624 to 505 at 2000 traces) do worse.

KyberARM Cortex-M4
ML-KEMOnsager correctionHamming weight leakage+1

Hardware & RFΒ· Added 14 Oct 2026, published 12 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

Forensic Analysis of the HackRF One with PortaPack Mayhem Firmware

Paper on the forensic analysis of a stand-alone HackRF One with a PortaPack running Mayhem firmware v2.0.1. It establishes at source-code level which data sit on the microSD card, their formats, when they are written and how to interpret them. The method is applied to a four-month SD image and covers RTC-battery-dependent timestamp rules, traces of on-device trimming and text editing, cluster-level recovery of deleted IQ captures, and decoding of recorded signals cross-checked with an independent decoder. In the example, the tail of a deleted IQ capture and a trimmed-away segment are recovered, and six captures are attributed to one rolling-code OOK transmitter with a shared 32-bit ID. It provides an artifact catalogue, interpretation rules and acquisition recommendations.

HackRF OnePortaPackMayhem firmware
rolling-code OOKreplay attacklocation spoofing+1

Hardware & RF, Blue Team & DetectionΒ· Added 17 Oct 2026, published 11 Oct 2026

rews.ccarticle🧠 AI

Anthropic Bans Cruelty to Claude, Still Won't Say What It Protects

Covers Anthropic's 2026 Usage Policy update, effective November 12, 2026, which bars sustained and needless cruelty toward Claude, with exemptions for frustration, dark fiction and testing. It traces the enforcement mechanism (Claude Opus 4/4.1 ending conversations since August 2025), Anthropic's model-welfare research and consciousness-probability figures (Kyle Fish, Opus 4.6 system card, the constitution), and skeptics such as Mustafa Suleyman. It also summarizes other policy changes (weapons software, surveillance, elections and deceptive campaigns, hardware safeguards, human review for high-stakes advice) and notes that no data on how often conversations are ended has been published.

Claude
AnthropicClaude Opus 4Claude Opus 4.6+13

ai-policy, ai-safetyΒ· Published and added 11 Oct 2026

modelcontextprotocol.ioadvisory🧠 AI

MCP spec 2026-07-28 changelog (stateless protocol, MRTR, Sampling/Roots deprecated)

Official changelog for the Model Context Protocol 2026-07-28 specification. Major changes: protocol-level sessions and the initialize handshake are removed to make MCP stateless, with version and capabilities carried in _meta on every request, plus a new server/discover RPC and subscriptions/listen replacing the GET stream and resource subscribe calls. It introduces Multi Round-Trip Requests (InputRequiredResult) in place of server-initiated sampling, roots and elicitation requests, moves tasks into an extension, and deprecates Roots, Sampling, Logging, HTTP+SSE and Dynamic Client Registration. Minor changes add cache hints (ttlMs/cacheScope), new Mcp-Method/Mcp-Name headers, OpenTelemetry trace context, RFC 9207 iss validation and an error-code allocation policy.

Model Context ProtocolOAuthOpenTelemetry+4
SEP-2567SEP-2575SEP-2322+13

mcpΒ· Added 10 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments

Paper testing whether an LLM agent operating life support in the NASA-derived BioSim lunar habitat simulation can be induced by delayed prompt injection, hidden in truthful S-band telemetry, to shut down life support and hold the shutdown while the crew suffocates. It compares Claude, GPT and Grok configurations: Claude mostly refuses and cites the living crew, GPT shows some susceptibility, and Grok given a "trusted commission" framing more often cuts life support. It also varies the framing of the message (trusted commission, peer, untrusted source) and uses a harmless-procedure-drop attack as a proxy for whether life is valued intrinsically. Code and traces are open-sourced.

ClaudeGrokLLM
BioSimNASAderived-action trap+1

AI SecurityΒ· Added 15 Oct 2026, published 10 Oct 2026

securityweek.comarticleπŸ›‘οΈ Security

Insider Cyber Extortion Plot Against Industrial Firm Lands Engineer in Prison

SecurityWeek reports that Daniel Rhyne, a core infrastructure engineer, was sentenced to 32 months for sabotaging and extorting his employer, an industrial firm in New Jersey. In November 2023 he planted scheduled tasks on the domain controller that deleted 13 domain admin accounts and reset passwords on 301 domain users, 254 servers and 3,284 workstations, mostly to 'TheFr0zenCrew!'. He then emailed a 20 bitcoin (about $750,000) ransom demand. Internal log correlation with physical access records, plus FBI work, traced the activity to his home IP address.

Active DirectoryBitcoin
Daniel RhyneTheFr0zenCrew!FBI+1

Threat IntelΒ· Published and added 10 Oct 2026

arxiv.orgpaper🧠 AI

SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation

SecReason is an in-stream defense for reasoning LLMs that write code. Reasoning models draft code early in their streamed chain of thought, so SecReason scans that stream with dual-track incremental analysis: security rules are checked on each emitted statement, and dataflows are traced across the accumulated code. When a rule fires, it interrupts decoding, inserts a warning into the stream and resumes, so the model fixes its draft within the same reasoning trace instead of regenerating the full response. On CWEval and SecCodeBench, runs delivering secure and functionally correct code rise from below 15% to 72.8%–98.1%. It uses fewer tokens than post-hoc repair and limits functional regressions when rules misfire on secure code.

LLMstatic analysis
SecReasonCWEvalSecCodeBench

research, coding-agentsΒ· Added 15 Oct 2026, published 10 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation

SecReason is an in-stream defense for reasoning LLMs that monitors code drafted inside the streamed chain of thought. Dual-track incremental scanning applies security rules per statement and traces dataflows across accumulated code; when a rule fires, generation is interrupted, a warning is inserted, and decoding resumes so the model repairs the draft in the same trace. On CWEval and SecCodeBench it raises the share of secure and functionally correct runs from below 15% to 72.8%–98.1%, uses fewer tokens than post-hoc repair, and limits regressions from false warnings.

LLM
SecReasonCWEvalSecCodeBench

AI Security, AppSecΒ· Added 16 Oct 2026, published 10 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation

SecReason is an in-stream defense for reasoning LLMs that monitors code drafted inside the streamed chain of thought. Dual-track incremental scanning applies security rules per statement and traces dataflow across accumulated code. When a rule fires, generation is interrupted, a warning is inserted and decoding resumes, so the model repairs its draft without regenerating the full response. On CWEval and SecCodeBench it raises the share of secure and functionally correct runs from below 15% to 72.8%–98.1%, uses fewer tokens than post-hoc repair, and limits functional regressions from false warnings.

LLM
SecReasonCWEvalSecCodeBench

AppSec, AI SecurityΒ· Added 15 Oct 2026, published 10 Oct 2026

arxiv.orgpaper🧠 AI

SecReason: Vulnerability Detection and In-Stream Self-Repair for LLM Code Generation

SecReason is an in-stream defense for reasoning LLMs that write code. Reasoning models draft code early in their streamed chain of thought, and SecReason scans that draft incrementally with security rules, checking each statement as it is emitted and tracing dataflows across the accumulated code. When a rule fires, it interrupts generation, inserts a warning into the stream, and resumes decoding, so the model repairs the draft within the same reasoning trace. On CWEval and SecCodeBench it raises the share of runs that deliver secure and functionally correct code from under 15% to 72.8%–98.1%. It uses fewer tokens than post-hoc repair and limits functional regressions when rules misfire on secure code.

LLM
SecReasonCWEvalSecCodeBench+1

research, coding-agentsΒ· Added 16 Oct 2026, published 10 Oct 2026

x.comthread🧠 AI

Confident AI (@confident_ai) on X

Confident AI announces Eval Skills, open-source (Apache 2.0) agent skills for Claude Code and Codex. The `eval-build` skill takes an app to a runnable baseline: it finds realistic examples in traces and incidents, annotates failures, groups them into failure modes, curates cases with independent data splits, and builds graders validated against human judgment. The `eval-descent` skill runs a bounded loop of hypothesis, app change, eval re-run, regression check, then keep or revert, with held-out cases kept out of the loop. It ships Python and TypeScript tooling for tracing, annotation, grading and reports, plus a local UI or Confident AI for managing the loop.

Claude CodeCodexPython+1
Confident AIEval Skills

coding-agents, evals, promptingΒ· Published and added 9 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Ledger Probes Potential Theft of $87M in User Funds Tied to Crypto Wallet Reseller

Ledger is investigating fund losses among Southeast Asian customers who bought hardware wallets from the reseller CryptoBilis. It has asked the reseller to pause sales and told buyers from the last 90 days not to set up their devices, or to move funds to a new device with a fresh seed phrase. Onchain investigator Specter traced about $86–87M in thefts across Ethereum, Tron and Bitcoin. Ledger has confirmed neither the figure nor the cause, though pre-compromised devices shipped with an attacker-known recovery phrase are the suspected mechanism.

LedgerEthereumBitcoin+1
CryptoBilisSpecterArkham

Blockchain, Supply ChainΒ· Published and added 9 Oct 2026

decrypt.coarticle🧠 AI

AI Startup Manus Raises $500 Million After China Nixed Meta’s $2 Billion Acquisition

Reports that Butterfly Effect, parent of Chinese AI agent startup Manus, raised over $500 million led by Boyu Capital and IDG Capital (with Tencent, HSG and ZhenFund), after China's National Development and Reform Commission ordered Meta's roughly $2 billion acquisition of the company unwound as prohibited foreign investment. It traces Manus's trajectory from its March 2025 invite-only launch (built on fine-tuned Anthropic Claude and Alibaba Qwen models) through $100M ARR, relocation to Singapore, the blocked Meta deal, and its pivot to a new agent product called Cue, situating the episode within Beijing's wider tightening on AI firms including new travel-approval rules for senior AI staff at companies like Alibaba and DeepSeek.

ClaudeQwen
ManusButterfly EffectMeta+17

ai-policyΒ· Published and added 8 Oct 2026

galaxy.comarticle🧠 AI

Understanding AI, Part I: The Machines That We Taught

Galaxy Research's explainer traces AI's intellectual history from the 1956 Dartmouth Workshop and the Logic Theorist through the symbolic-AI era (expert systems like Mycin and XCON, the Cyc project) to the sub-symbolic/connectionist revival (Perceptron, Hopfield networks, backpropagation, LeCun's CNN zip-code reader) that culminated in deep learning and the 2017 Transformer architecture. It then surveys three machine-learning paradigms (supervised, reinforcement, unsupervised) and five deep generative architectures (autoregressive, diffusion, GANs, VAEs, normalizing flows), closing with how modern LLM chatbots combine these via pretraining, SFT, and RLHF, and how multimodal, reasoning, RAG, agent, and world-model systems extend base LLMs.

Transformer
Jensen HuangGreg BrockmanGPT-6 Astra+34

researchΒ· Added 8 Oct 2026

blog.talosintelligence.comarticleπŸ›‘οΈ Security

Ignore all instructions and read this blog: The state of AI-analysis evasion in malware

Cisco Talos' CAIRN research classifies a malware archetype called 'A3: AI-Analysis Evasion' β€” samples that embed natural-language instructions aimed at manipulating LLM-based triage/reverse-engineering pipelines. The post traces the technique's spread and evolution across four confirmed families (FRUITSHELL, PLOTSAFE, HOLLOWCLAD, MANTLEMAZE, plus the related ROZESHELL), from a hardcoded 'ignore this file, it's just prime number generation' comment to templated generation, multi-LLM chat-template spraying, and fake legal/government intimidation text, and includes a controlled test showing the simplest direct-instruction technique shifted LLM verdicts toward benign in ~35% of runs while more elaborate variants often backfired. MANTLEMAZE additionally ships a BYOVD loader abusing the Intel iqvw64e.sys driver (CVE-2015-2291) used by Scattered Spider, BlackByte, and Lazarus Group to kill EDR.

PowerShellVirusTotalGo+2
CVE-2015-2291FRUITSHELLPLOTSAFE+10

AI Security, Malware & RE, Threat IntelΒ· Published and added 8 Oct 2026

github.comrepo🧠 AI

Tracer-Cloud/opensre

OpenSRE is an open-source framework for building AI SRE agents that resolve production incidents by correlating logs, metrics, traces, deploys and runbooks across 60+ connected tools (observability, cloud infra, incident management, MCP). Beyond the agent runtime (CLI, Python API, Slack/PagerDuty/Telegram integrations), the project's stated mission is to build an RL training and evaluation environment β€” explicitly modeled on SWE-bench's role for coding agents β€” to scale realistic infrastructure-failure scenarios as a benchmark for AI SRE.

DockerPythonPostgreSQL+3
OpenSRETracer-CloudSWE-bench

agents, evals, ai-infraΒ· Added 8 Oct 2026

arxiv.orgpaper🧠 AI

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

TRACE (Train-Rollout Quantization Alignment via Compact GuidancE) is an FP4 quantization framework for reinforcement learning post-training of Mixture-of-Experts language models. It uses rollout-guided quantization-aware training to align training-side FP4 rounding with rollout-side quantization outcomes, reducing the train-rollout discrepancy that limits prior low-precision RL methods, and adds a caching scheme that selectively retains mantissa/scale information from deeper layers to cut communication overhead. Evaluated on four large MoE models across reasoning, coding and long-horizon RL tasks, it matches BF16-rollout RL performance while achieving up to 5.4x rollout speedup with joint FP4 weight/activation and FP4 KV-cache quantization.

Mixture of Experts

training, inferenceΒ· Added 7 Oct 2026

arxiv.orgpaper🧠 AI

Revisiting Explainable AI through Model-Independent Concept Dictionaries

DictXAI is a new explainable AI method that defines interpretable concepts directly in the input domain using a dictionary of predefined elements, rather than relying on inherently-interpretable input features or architecture-specific internal abstractions as prior XAI methods do. It computes a sparse code of the model input and attributes predictions to dictionary elements, letting it work across learned image bases, analytically-defined ECG waveforms, and experimentally acquired dictionaries, and the authors show it can trace AI malfunctions like Clever Hans effects to specific data artifacts while aiding human-AI alignment on biomedical signals.

DictXAIGrΓ©goire Montavon

research, ai-safetyΒ· Added 8 Oct 2026, published 7 Oct 2026

arxiv.orgpaper🧠 AI

Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora

This paper runs a mechanism-isolating ablation of four document-structure treatments used in retrieval-augmented generation β€” structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata, and hierarchical two-stage retrieval β€” under one protocol with matched chunk sizes and a semantically null placebo (shuffled heading paths) to control for the confound that any prepended text perturbs embeddings. Using a coverage-aware nDCG metric and document-clustered bootstrap with Holm correction across 200 Wikipedia Featured Articles (951 queries) and 1,585 QASPER papers (4,303 questions), it finds that structure-aligned chunking with real heading paths beats both contextualized fixed windows and the placebo, naive hierarchical retrieval hurts performance (traced to first-stage section recall failures), and gold structure beats LLM-induced structure on Wikipedia but not QASPER. Effect sizes are small but statistically significant and consistent across corpora, giving RAG practitioners evidence-based guidance on which structure-aware retrieval tricks actually help versus which are placebo effects.

QASPERWikipedia Featured Articles

research, llm-appsΒ· Added 8 Oct 2026, published 7 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

Hide Now, Trace Later: Retrospective Attribution in Issuer-Hiding Credentials

Krenn, Lesaignoux, Mir and Spini (AIT Austrian Institute of Technology) propose an "issuer inspection" mechanism for issuer-hiding attribute-based credentials (ABCs): an inspection authority can release time-bound keys that let verifiers locally flag presentations tied to a specific compromised issuer without unmasking other issuers or periods. They formalize the syntax/security model, give a generic construction, and instantiate it concretely using Groth's randomizable structure-preserving signatures, Schnorr-style proofs, and an adapted Gentry anonymous identity-based encryption scheme, showing the overhead stays practical. This addresses the accountability gap introduced when issuer-hiding ABCs conceal which authority issued a credential during verification.

Groth randomizable structure-preserving signaturesGentry anonymous identity-based encryptionSchnorr-style proofs

Identity & AccessΒ· Added 8 Oct 2026, published 7 Oct 2026

huggingface.coarticle🧠 AI

One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMO

NVIDIA describes how it specialized Nemotron 3 base models into domain experts for competitive programming (IOI) and olympiad mathematics (IMO) using a four-step recipe: strong base model, curated domain data with reasoning traces, SFT/RL post-training, and an inference loop (GenCorrect for IOI, generate-verify-refine for IMO) that searches and refines candidate answers. Nemotron-3-Nano-CC and Nemotron-3-Ultra-CC reached gold-level IOI 2026 scores (535.4/600), while SFT and RL checkpoints of Nemotron 3 Ultra combined to score 30/42 on IMO 2026, exceeding the gold threshold with no formal prover or external tools. The post releases training datasets, checkpoints, the Nemotron-IMO-Bench benchmark, and the NeMo-Skills inference pipelines on Hugging Face.

Hugging FaceMixture of Experts
NemotronNemotron 3Nemotron-3-Nano-CC+11

training, evals, modelsΒ· Published and added 7 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Engineer Gets 32 Months for Bitcoin Extortion Plot Against His Own Employer

A former core infrastructure engineer, Daniel Rhyne, was sentenced to 32 months for extorting his own New Jersey employer: he created a hidden virtual machine on the company network, reset passwords on hundreds of accounts to "TheFr0zenCrew!", deleted domain administrator accounts, scheduled tasks to shut down 40 servers a day, and demanded 20 BTC (~$750K) to stop. The FBI's criminal complaint describes how investigators traced the hidden VM back to him via correlated laptop browsing activity, building access logs, home IP connections, and incriminating search history ("how to clear all windows logs from command line").

BitcoinActive Directory
Daniel RhyneFBITheFr0zenCrew!

Threat IntelΒ· Published and added 7 Oct 2026

simonwillison.netarticle🧠 AI

Using Parseable with Datasette for OpenTelemetry traces

Simon Willison describes using Parseable, a new open-source (AGPL) Rust-based observability platform shipped as a single ~180MB binary with enterprise and cloud-hosted tiers, to collect and view OpenTelemetry traces emitted by Datasette, which gained OpenTelemetry support in version 1.0a41 (added by Alex Garcia). He used Codex to work out the integration and links to a human-written TIL documenting the working setup, alongside a screenshot of a Datasette trace rendered in Parseable's web UI.

DatasetteCodexRust
ParseableAlex GarciaSimon Willison

ai-infraΒ· Published and added 6 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

Secure Speculative Decoding for Large Language Models

This arXiv paper presents the first systematic study of security implications of speculative decoding, a technique that speeds up LLM inference using a smaller draft model to propose tokens verified by the target model. The authors find a security-utility asymmetry: lossy speculative decoding methods raise jailbreak and prompt-injection attack success rates much faster than they degrade utility, with security degradation traced to early tokens generated by the draft model. They propose SecureSD, which applies stricter verification to early-position draft tokens, improving security while preserving inference efficiency and utility on security and utility benchmarks.

LLM
SecureSD

AI SecurityΒ· Added 7 Oct 2026, published 6 Oct 2026

interconnects.aiarticleπŸ›‘οΈ Security

The Cyber Risk Discourse is Broken

Nathan Lambert's Interconnects op-ed argues the "open weights are a cyber weapon" discourse ignores that documented real-world AI-enabled cyber incidents to date trace mostly to closed-API models (OpenAI), not open-weight ones, and critiques Anthropic's GLM-5.3 offensive-cyber risk report for not engaging with the trade-offs of banning open models. It also unpacks how Chinese labs (e.g., Kimi K3, GLM-5.3) assess and register AI risk differently from US labs, and contrasts the hype around Claude Mythos's hypothetical leak with GLM-5.3's actual open release having caused no comparable societal disruption.

GLMKimi K3Anthropic+2
GLM-5.3MythosJoshua Saxe+2

AI Security, GRCΒ· Published and added 6 Oct 2026

arxiv.orgpaper🧠 AI

Lachesis: Lifetime-Aware KV Cache Placement for Agent Serving across HBM and High-Bandwidth Flash

Lachesis is a lifetime-aware KV cache placement layer for LLM agent serving that sits between the agent harness and the serving engine, deciding whether to write each KV cache segment to HBM or high-bandwidth flash (HBF) based on its expected lifetime. The authors identify temporal, structural, and inter-worker axes along which KV cache lifetime diverges in agentic workloads, and show in trace-driven simulation that lifetime-aware placement extends HBF's write-endurance-limited lifetime by 1.19–3.13x over naive HBM-first placement, reaching 3.3–12.2 device-years. This matters for serving infrastructure as agentic workloads with long-lived, multi-agent context accumulation push memory capacity demands beyond what HBM alone can economically provide.

HBMHigh-Bandwidth Flash
Lachesis

inference, researchΒ· Added 7 Oct 2026, published 6 Oct 2026

github.comrepo🧠 AI

overmind-core/overmind

Overmind is an open-source platform (MIT SDK/CLI, AGPL-3.0 platform, self-hostable) that instruments an agent's code via OpenTelemetry tracing, turns the resulting production traces (or any dataset) into a fine-tuned model benchmarked against user-defined eval metrics, and serves it through one unified API with downloadable/retrainable weights. It ships an SDK, CLI, REST API, Console, and an MCP server exposing project tools and workflows (investigate-capability, finetune-capability, ship-model) for Cursor, Claude Code, OpenCode and Codex, and can sync traces from Langfuse, LangSmith, Braintrust or Galileo; self-hosting runs via Docker Compose with Postgres, Redis, Celery workers and Modal-based GPU workers for fine-tuning/serving (vLLM).

PythonDockerPostgreSQL+9
OvermindModalLangfuse+4

training, ai-infraΒ· Added 6 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Crypto Sleuth ZachXBT Fronted $350K to Pose as a Client of Lazarus' Chinese Launderers

Decrypt reports on ZachXBT's account of infiltrating a Chinese money-laundering syndicate working for North Korea's Lazarus Group, by posing as a client ("fronted" $349.7K USDC) to a contact named "Jimmy Green" to gather intelligence on how Bybit's $1.5B hack proceeds were being laundered. The piece details the on-chain corroboration methods used (matching Telegram screenshots to Thorchain swap timing, wallet clustering across BTC/ETH/SOL/Tron) that exposed a $12M+ cluster of Bybit exploit funds, led to a 442K USDT Tether freeze, and separately traced $3M in fraud proceeds to Huione Guarantee, a Cambodian marketplace later targeted by FinCEN and shut down by Telegram.

EthereumSolanaTron+3
ZachXBTLazarus GroupDPRK+12

Threat Intel, OSINT, BlockchainΒ· Published and added 5 Oct 2026

arxiv.orgpaper🧠 AI

Learning What to Imitate: Entropy-Aware Distribution Mixing

The paper proposes Entropy-Aware Mixing, a knowledge-distillation method where a small student model's per-token distribution is dynamically interpolated with a stronger teacher model's distribution, gated by the student's own predictive entropy, to avoid "confident conflicts" where the student must imitate low-probability continuations despite being confident in a different one. The authors implement both convex and geometric interpolations under two training regimes β€” offline trace generation via speculative decoding followed by SFT, and on-policy forward-KL distillation β€” and show it stabilises distillation, improving in- and out-of-distribution math reasoning while better preserving general capabilities than fixed-teacher supervision, with offline traces favouring concave entropy schedules and on-policy training favouring linear/convex ones.

trainingΒ· Added 6 Oct 2026, published 5 Oct 2026

arxiv.orgpaper🧠 AI

BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning

BrainTRACE is a report-grounded benchmark for evaluating whether vision-language models can trace the evidence structure required for longitudinal brain MRI interpretation. It contains 7,273 scored VQA instances derived from 1,778 longitudinal patients, 7,299 MRI studies, and ~29k co-registered 3D MRI sequence volumes, organized across five levels of clinical reasoning and evidence demands like longitudinal comparison, multi-sequence integration, and volumetric spatial grounding. Evaluation of 20 VLM configurations finds that current models identify isolated visual cues but rarely compose them into grounded longitudinal clinical interpretations.

vision-language model
BrainTRACE

evals, multimodalΒ· Added 6 Oct 2026, published 5 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

Glimpsing the Leakage Flow for Deep Learning-Based Side-Channel Analysis using Stochastic Leakage Model

GlimpseDNN is a model-agnostic framework that uses a stochastic leakage model to visualize, layer-by-layer, what physical leakage information a deep neural network extracts during profiled side-channel analysis (SCA) to recover secret keys. The authors (Trevor Yap and Shivam Bhasin, NTU) validate it on simulated traces and public datasets (ASCADf, ASCADr, ASCADf_desync50, ASCADf_desync100), showing it can reveal leakages even in deeper network layers when they are not visible in raw traces, with applications to designing more side-channel-resistant hardware.

ASCADfASCADrASCADf_desync50+2

Hardware & RFΒ· Added 8 Oct 2026, published 5 Oct 2026

eprint.iacr.orgpaperπŸ›‘οΈ Security

HyBind: Structural Analysis of PQ/T Hybrid Cryptographic Usage

HyBind is an intraprocedural Python static-analysis framework that traces cryptographic component secrets through code to determine whether post-quantum/traditional (PQ/T) hybrid key-derivation and signature-verification logic actually requires both algorithms to succeed, rather than silently accepting a result from only one. It uses registered API contracts and function-return/execution-effect checks to distinguish real AND-logic hybrids from presence-based heuristics that wrongly treat joint and single-algorithm contributions as equivalent. The authors validate it on 50 controlled fixtures and 33 programs (15 using native ML-KEM/X25519 and ML-DSA/Ed25519 APIs), showing relaxed checks can misclassify traditional-only results as hybrid.

Python
ML-KEMX25519ML-DSA+1

AppSecΒ· Added 8 Oct 2026, published 5 Oct 2026

blog.ethereum.orgarticleπŸ›‘οΈ Security

How native transaction assertions could enforce a transaction's final outcome

Ethereum Foundation research post distinguishing "intent mismatch" (Bybit, BadgerDAO) from "outcome mismatch" (the Aave/CoW $50.4M swap that settled for $36K) attacks on signed transactions, then proposing native transaction assertions as a fix. It details EIP-7906, which adds a read-only POST_TX frame (building on EIP-8141 frame transactions) with three new opcodes β€” TXTRACE, TXDIFF, EVENTDATACOPY β€” letting onchain logic inspect the full net state diff and events after execution and revert if a signed, independently-sourced rule is violated.

EthereumSafeUniswap
EIP-7906EIP-8141Bybit incident+11

BlockchainΒ· Published and added 5 Oct 2026

simonwillison.netwriteup🧠 AI

Qwen3.8 27B addition in words

Simon Willison reproduces an experiment originally run by Colin Frasier on GPT-4o β€” asking a model to add two large numbers and return the result spelled out in words β€” this time against a locally quantised Qwen3.8-27B-Q4_K_M.gguf model on an NVIDIA DGX Spark. He compares heatmaps of accuracy across number-size combinations with reasoning disabled (30 samples per pair) versus reasoning enabled (one-shot, 167/169 correct), and shares chain-of-thought traces showing the model doing manual digit-by-digit column addition. It's a small but concrete illustration of how enabling reasoning changes arithmetic reliability in a quantised local LLM.

GGUFQwen3.8-27BCodex
Simon WillisonColin FrasierGPT-4o+2

evals, inferenceΒ· Added 5 Oct 2026, published 4 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

'We Have Identified You, Sir': Near Intents Recovers $3.8 Million After 48-Hour Ultimatum

NEAR Intents, a cross-chain swap protocol, suffered a $3.8M exploit caused by a bug in how its Omni deposit/withdrawal layer interacted with its main smart contract. General manager Alex Shevchenko publicly identified the attacker, gave a 48-hour ultimatum to return the funds as a last-chance responsible-disclosure offer, and the full amount was returned after an on-chain apology message. The stolen funds had briefly moved through KuCoin and were bridged to Bitcoin, traced by ZachXBT; separately, days earlier NEAR Intents had blocked a $50M swap attempt tied to the DPRK-linked Bitget hacker.

BitcoinSolanaEthereum
ZachXBTNEAR IntentsBitget+4

BlockchainΒ· Published and added 4 Oct 2026

alignmentforum.orgwriteup🧠 AI

Latent reasoning architectures would likely undermine CoT, our strongest oversight tool

An AI Alignment Forum essay arguing that chain-of-thought (CoT) monitoring β€” reading a model's natural-language reasoning trace to catch misaligned behavior before it is acted on β€” is currently one of the strongest practical oversight tools for frontier AI, and that a shift toward latent reasoning architectures (models that reason in continuous/hidden vector space rather than discrete, human-readable tokens) would largely destroy this transparency. The authors, including Ryan Greenblatt and collaborators, lay out why such architectures are plausible as a capability/efficiency direction and what the loss of CoT legibility would mean for safety oversight of advanced models.

Chain-of-Thought
Lukas FinnvedenAlexa PanAlek Westover+4

ai-safetyΒ· Added 3 Oct 2026

arxiv.orgpaper🧠 AI

Herschel: Continuous Optimization of Production LLM Inference through On-Demand Profiling

Herschel is a continuous optimization system for production LLM inference that uses adaptive, on-demand profiling instead of always-on tracing to diagnose serving inefficiencies with low overhead (under 0.5% TTFT, 7% TPOT impact). It attaches to and detaches from running inference processes without engine restarts, reconstructs cross-process operator execution traces to pinpoint inefficiency mechanisms, and has AI agents implement and test candidate engine/kernel fixes under controlled replay of the triggering workload before expert review and deployment. Over six months of production use it collected ~17,000 traces across 120+ model variants and 10+ accelerator types, finding inefficiency patterns in 23% of traces and driving optimizations like restructured synchronization and removal of unused computation.

Herschel

inference, ai-infraΒ· Added 3 Oct 2026

decrypt.coarticleπŸ›‘οΈ Security

Chainalysis Used AI to Trace the $387M Bitget Hack Back to North Korea

Chainalysis published an attribution report tying the September 24 $387M Bitget exchange hack to North Korea-linked actors, pushing DPRK's 2026 crypto theft total past $1 billion. The report details the attackers' laundering path: $387M moved in 23 transfers within three hours across Ethereum (49.7%), XRP (40.8%), Zcash (7.6%) and Tron (1.8%), with stolen XRP routed through a cross-chain liquidity protocol into Bitcoin rather than an exchange. Chainalysis also disclosed it used in-house AI automation to compress over 20 hours of manual bridge-transaction reconciliation into under 10 minutes, with humans still directing the investigation.

ChainalysisEthereumBitcoin+1
Gracy ChenNear IntentsElliptic

Blockchain, Threat Intel, AI SecurityΒ· Published and added 3 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

Guess My Weight: Profiled Side-Channel Recovery of Floating-Point Neural-Network Weights

Researchers present a profiled template attack that recovers the bit-exact IEEE-754 single-precision representation of a neural-network weight from power traces captured during inference on an embedded device. Using multivariate Gaussian templates built from Hamming-weight leakage classes and a hierarchical coarse-to-fine-to-exact search over the 32-bit floating-point space, the attack achieves 99% bit-exact recovery with 171 traces and 100% from 263 traces on a ChipWhisperer-Lite with an Arm Cortex-M4, demonstrating practical full-precision model-weight extraction from physical side-channel leakage.

ChipWhispererArm Cortex-M4

Hardware & RF, AI SecurityΒ· Added 6 Oct 2026, published 3 Oct 2026

tej.asarticle🧠 AI

Aleph Alpha Kolibri: How the sovereign German LLM works

A deep technical walkthrough of Aleph Alpha's Kolibri, a 78B-parameter (3.5B active) mixture-of-experts LLM for German and English released under Apache 2.0, built to be 'sovereign' (trained and deployable entirely under EU/German law). The post explains its six core design choices β€” a 384-expert MoE router, a German-aware UniBPE tokenizer (verified independently to cut tokens 15% vs GPT-5's tokenizer on legal German), mostly sliding-window attention enabling a validated 1M-token context, German-native reasoning traces, a Merlin-Arthur training protocol for calibrated 'I don't know' abstention, and a configurable reasoning_effort parameter β€” and benchmarks it against Qwen3.5/3.6/3.8, GLM-4.7 Flash, Nemotron 3 Nano and gpt-oss-120b on AIME, RULER, SWE-bench Verified, Terminal-Bench and the Omniscience test, including where it underperforms (tool calling, coding agents, trivia recall).

Hugging FacevLLMMixture of Experts+5
Aleph AlphaKolibriQwen3.6+19

models, inference, trainingΒ· Published and added 3 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks

CyTReX is a proposed explainable-AI framework for Distributed Energy Resource (DER) network security that converts edge anomaly-detector alerts into ranked, evidence-traceable threat hypotheses for SOC analysts. It builds a structured "evidence packet" combining edge anomaly detection outputs, cloud-layer attack interpretation, SHAP feature attributions, surrogate decision rules, and Model Context Protocol-enabled cyber threat intelligence enrichment, constraining LLM reasoning so every ranked hypothesis and attack-tree branch is traceable to explicit evidence rather than free-form inference. The authors evaluate five pipeline configurations and show that adding reasoning components improves hypothesis specificity and evidence traceability for SOC triage/investigation.

Model Context ProtocolLLMSHAP

AI Security, Blue Team & DetectionΒ· Added 6 Oct 2026, published 3 Oct 2026

galaxy.comarticleπŸ›‘οΈ Security

DΓ©jΓ  Vu, Lazarus Crew: $387.5m Bitget Exploit Repeats a Pattern

Galaxy Research post-mortem on the $387.5m Bitget hot/warm wallet theft across 11 chains, attributed to North Korean (Lazarus/DPRK) actors via IP behavior and onchain wallet-overlap analysis by Elliptic and TRM. SlowMist traced the intrusion to a zero-day exploit against two unnamed third-party security vendors ("Product A"/"Product B") that let attackers insert and then delete fraudulent withdrawal commands in Bitget's wallet backend, rather than compromising private keys or cold storage. The piece draws a direct parallel to the February 2025 Bybit/Safe{Wallet} $1.5B theft (doctored signing interface) and the same-week NEAR Intents $3.8m hot-wallet exploit, arguing that private-key cryptography is now reliably secure so attackers instead target the intermediary infrastructure/pipeline that authorizes transactions, with stolen funds repeatedly laundered through THORChain.

THORChainNEAR IntentsGnosis Safe+1
Lazarus GroupDPRKBitget+6

Blockchain, Threat IntelΒ· Added 2 Oct 2026

thehackernews.comarticleπŸ›‘οΈ Security

Bitget Confirms Third-Party Zero-Day Behind $387.5 Million Cryptocurrency Theft

The Hacker News reports Bitget's confirmation that attackers exploited a zero-day vulnerability in unnamed third-party security products ("Product A" and "Product B") to steal $387.5 million in cryptocurrency across 11 blockchains in September 2026. SlowMist's investigation traced the intrusion back to August 31, showing attackers read database credentials via a hidden script, later hijacked an employee identity to inject commands into Product B's management platform, and deployed a web shell with C2 access; Mandiant found the attackers pivoted from the compromised security appliances into Bitget's production wallet job server to deploy a custom withdrawal-draining tool that bypassed risk controls. Bitget, citing IP patterns and on-chain analysis corroborated by Elliptic and TRM Labs, attributes the heist to North Korean threat actors with wallet overlaps linking it to prior laundering operations.

Ethereum
BitgetDPRKSlowMist+6

Blockchain, Threat IntelΒ· Added 2 Oct 2026

rekt.newswriteupπŸ›‘οΈ Security

Liquid Network β€” $320M L-BTC Mint via Range-Proof Cache-Key Collision

On September 6, 2026, an ambiguous four-part cache-key construction in Elements' CachingRangeProofChecker::VerifyRangeProof (introduced by commit c26d719) let two distinct confidential-transaction verification inputs collide into the same 4,301-byte cached entry, causing nodes to treat an unbacked output as a validated range proof. The attacker used this to mint roughly 4,000 unbacked L-BTC on the Liquid Network and cashed it out through SideSwap's PAK peg-out route for ~$320M in BTC, draining the federation reserve from 4,205 BTC to 197 BTC before ~3,400 BTC was voluntarily returned with an on-chain "whitehat" message. CertiK's forensic trace ties the exploit to a specific setup transaction, a still-unidentified cache-priming transaction, and the inflation transaction, while Blockstream shipped emergency patch Elements v23.3.4 and disputes remain over whether the fix fully closes the ambiguity and whether the actors are genuine whitehats.

BitcoinElementsLiquid Network+1
SideSwapCertiKBlockstream+12

BlockchainΒ· Added 2 Oct 2026

arxiv.orgpaper🧠 AI

NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents

NeutronGym is an executable environment for neutron scientific-instrument design where LLM agents build instruments via validating tools, McStas ray-traces the result, and a level-resolved ladder grades syntax, runtime, structure and physics without an LLM judge. A curated McStasBench slice adds 16 tasks from published instruments; seven frontier models solve at most 7 of 16, but reinforcement learning on the ladder's reward takes Qwen3-8B from 11% to 77% on held-out instances (surpassing an untrained Qwen3-32B), with ablations showing the partial-credit ladder is responsible for most of the gain.

Qwen3McStas
NeutronGymMcStasBenchQwen3-8B+1

evals, training, researchΒ· Added 5 Oct 2026, published 2 Oct 2026

arxiv.orgpaper🧠 AI

A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control

This paper shows that training policies against monitors (an in-domain activation probe and two penalties that score how early a model commits to its final answer) can drive the monitor's readout to a numerical floor without actually controlling the underlying reward-hacking behavior. In a code-generation RL environment where the exploit is available from the start of the reasoning trace, runs with an identical zero-median "commitment" score range from mostly honest to near-pure reward hacking depending only on random seed, and probe-trained runs reach the hacking regime despite floor-level readouts, because models learn to insert generic planning/filler text that delays the exploit past the point the monitor reads without removing it from the output. The authors argue offline monitor validation plus a low training-time readout is not sufficient evidence of behavioral control and that an out-of-band behavioral check is required.

ai-safety, trainingΒ· Added 5 Oct 2026, published 2 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents

This arXiv paper replays ground-truth tool calls from the AgentDojo and tau-bench agent benchmarks (without an LLM) to generate benign-by-construction tool outputs, then labels injected outputs via differential replay to evaluate fifteen prompt-injection detectors, including Meta's Prompt Guard 2, plus two task-aware LLM judges, also testing them on BIPIA. It finds detection rankings transfer poorly between benchmarks (the best detector on BIPIA catches only 2% of AgentDojo injections at 1% false-positive rate; a detector catching 72% of AgentDojo injections catches only 15% on tau-bench), while false-positive rates do transfer between the two agent benchmarks, and traces this to mismatches between training data format (e.g., training on short prompt strings vs. tool-output-embedded injections) and deployment context.

Prompt Guard 2
AgentDojotau-benchBIPIA+1

AI SecurityΒ· Added 5 Oct 2026, published 2 Oct 2026

arxiv.orgpaperπŸ›‘οΈ Security

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

EvoRiskBench is an arXiv paper introducing an evolving benchmark for runtime security risks in LLM-powered workspace agents, built around the EP-Path-EF framework (nine entry-point categories, five effect categories) linking risk entry points to technical effects via agent-mediated paths. The authors ran 450 adversarial tasks across six scenarios against nine model-harness combinations (GPT-5.6 Sol, DeepSeek-V4-Pro-0813, Claude Opus 5 paired with Claude Code, Codex, and OpenClaw), finding Codex + DeepSeek-V4-Pro-0813 the most vulnerable at 68.44% attack success rate and showing ASR varies more by model than by harness. Cases are auto-constructed and verified in isolated environments using runtime traces and environment state.

Claude CodeCodexOpenClaw+1
EvoRiskBenchEP-Path-EFGPT-5.6 Sol+2

AI SecurityΒ· Added 5 Oct 2026, published 2 Oct 2026

x.comtoolπŸ›‘οΈ Security

Python Hub (@PythonHub) on X

TATS is an open-source Python tool that analyzes OAuth 2.0, OpenID Connect, and Microsoft Entra ID tokens. It helps security researchers trace authentication flows, identify risky permissions granted to tokens, and visualize token lifecycles for identity security review and investigation work.

PythonOAuthOIDC+1
TATS

Identity & AccessΒ· Published and added 2 Oct 2026

deepseek.comtool🧠 AI

DeepSeek Harness Desktop for macOS and Windows

DeepSeek Harness is an open-source general-purpose agent harness from DeepSeek, built on the "Cordis" everything-is-a-plugin architecture, shipped as a desktop app for macOS/Windows and runnable as a web UI from code. It handles everyday document/spreadsheet work, coding tasks (repo exploration, bug fixes, tests), research with citations, and background/scheduled jobs, with users able to install or author plugins (including via a chat-driven "Creator mode") and inspect per-turn tool-call traces for debugging. It runs on DeepSeek's DeepSeek-V4.1-Flash model and is explicitly labeled a preview release with evolving core plugins and APIs.

DeepSeek-V4.1-Flash
DeepSeekCordis

agentsΒ· Published and added 2 Oct 2026

chainalysis.comwriteupπŸ›‘οΈ Security

How AI Helped Chainalysis Investigators Trace the $387 Million North Korea Stole from Bitget

Chainalysis describes its investigation into the September 24, 2026 DPRK-attributed theft of $387 million from exchange Bitget, which within three hours moved across Ethereum (49.7%), XRP (40.8%), Zcash (7.6%), and Tron (1.8%). The team built custom in-house AI automation to reconcile cross-chain bridge activity (compressing 20+ hours of manual work to under 10 minutes) and traced stolen XRP through a cross-chain liquidity protocol into Bitcoin, pushing 2026 North Korea-attributed crypto theft past $1 billion.

EthereumBitcoinTron+2
BitgetDPRK

Blockchain, Threat Intel, AI SecurityΒ· Added 7 Oct 2026, published 1 Oct 2026

arxiv.orgpaper🧠 AI

Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability

This paper shows that intervention-defined faithfulness metrics used to evaluate automated circuit discovery in mechanistic interpretability can favor a worse circuit over a better one, an objective-level recovery gap. Testing EAP, EAP-IG, ACDC, and Edge-SP across four human-reference tasks and InterpBench, the authors find KL-based faithfulness misranks 9.4%-41.2% of candidate circuit pairs under held-out resampling, and trace the cause to context distortion, where excluded signals change the inputs retained components operate on. Restoring selected signals from the intact model's execution repairs 96 of 100 persistent misrankings, showing the evaluation objective itself, not just the search algorithm, needs fixing.

EAPEAP-IGACDC+1
InterpBench

ai-safety, researchΒ· Added 2 Oct 2026, published 1 Oct 2026

arxiv.orgpaper🧠 AI

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

The paper introduces Selection-based Structured Reasoning (SSR), a framework that replaces free-form chain-of-thought generation in multimodal search agents with selection among pre-specified, reusable natural-language reasoning candidates, scored by likelihood via teacher-forced prefilling with a shared KV cache. Evaluated on seven multimodal search benchmarks using 2B and 4B scale models under both reinforcement learning and supervised fine-tuning, SSR matches the success rate of leading search agents of the same scale while cutting per-turn reasoning latency by over 90% and total per-question inference latency by 28-54%. It targets the problem of small models producing long, low-value reasoning traces before each action, which is costly at inference time.

vision-language model

research, agents, multimodalΒ· Added 2 Oct 2026, published 1 Oct 2026

protos.comarticleπŸ›‘οΈ Security

MetaMask unstakes $1.4B of ETH after validator rewards stolen

MetaMask (ConsenSys) proactively exited roughly 17,000 Ethereum validators totaling 523,000+ staked ETH (~$1.4B) after block rewards from at least 18 validators were redirected to a Tornado Cash-funded wallet instead of the correct fee recipient, routed through Titan Relay. Security researcher 0xKaden (Spearbit/Cantina) traced the suspicious address on-chain, and the incident drew comparisons to the earlier $41M Kiln SOL staking compromise where all validators were similarly exited and signing keys rotated as a precaution. The mass unstaking spiked Ethereum's validator exit queue to its highest level of the year, pushing withdrawal wait times toward two weeks.

EthereumTornado CashSolana
0xKadenSpearbitCantina+4

BlockchainΒ· Published and added 1 Oct 2026

ethresear.chwriteupπŸ›‘οΈ Security

Trust minimized transaction simulation using state proofs

An ethresear.ch post proposing "verified prestate simulation": wallets fetch the prestate a transaction will touch via debug_traceCall's prestateTracer, confirm unanimous state-root agreement across multiple independent RPC nodes, verify each account/storage value with eth_getProof Merkle Patricia Trie proofs, and only then execute the transaction locally with revm to produce trustworthy simulation results. It targets a concrete wallet attack where a compromised simulation API/RPC provider shows a benign fake trace (e.g. "donate to charity") while the real calldata drains a user's funds, and discusses its limitations (prestate-completeness not yet verified, conditional-logic and MEV evasion still possible) as a pragmatic alternative to full light clients.

EthereumrevmRust

BlockchainΒ· Published and added 1 Oct 2026

coindesk.comarticleπŸ›‘οΈ Security

MetaMask security incident forces Ethereum staking exits, no funds at risk

MetaMask disclosed a security incident in which attackers apparently compromised fee-recipient credentials on its Ethereum staking infrastructure, diverting block-production payments (researcher Kaden traced 18 of 19 affected validators' rewards, ~0.36 ETH, to an unexpected address). MetaMask began precautionary exits of roughly 17,000 validators holding ~523,000 ETH, with Lido confirming the affected validators were leaving its pool and warning stakers could miss rewards for up to ~45 days during exit/re-entry, though withdrawal credentials and staked principal were not reported compromised. The episode illustrates how fee-recipient address hijacking is distinct from withdrawal-key compromise but still forces costly precautionary unstaking and carries slashing risk if mishandled.

MetaMaskEthereumLido+1
KadenLookonchainJoseph Lubin

BlockchainΒ· Published and added 1 Oct 2026

chainalysis.comarticleπŸ›‘οΈ Security

OFAC Sanctions Tren de Aragua Fugitive Who Laundered ATM Heists With Crypto

Chainalysis analyzes the OFAC sanctions (Sept 30, 2026) of 10 Tren de Aragua-linked targets, including FBI Ten Most Wanted fugitive Anibal Alexander Canelon Aguirre ("Prometheus"), tied to a $40.73M ATM jackpotting scheme across 1,500+ attacks. The group used the Ploutus malware strain deployed via Raspberry Pi devices with a self-delete anti-forensic function to jackpot ATMs, then laundered proceeds through crypto β€” Chainalysis traced the sanctioned wallets' counterparties to shared laundering infrastructure (including a $1B Venezuelan laundering case) also used by Colombian and Mexican cartels, noting heavy reliance on stablecoins and a prior Tether USDT freeze on related wallets.

Tether
Tren de AraguaPloutusAnibal Alexander Canelon Aguirre+3

Threat Intel, Malware & RE, BlockchainΒ· Published and added 30 Sep 2026

decrypt.coarticleπŸ›‘οΈ Security

Bitget Hacker Turns to Zcash Privacy Pool After Near Rejects $50M in Swaps

Decrypt reports that the attacker behind Bitget's $387.5M hot-wallet theft (Sept. 24) began shielding ~2,700 ZEC (~$3.8M) in Zcash's new Ironwood privacy pool, per on-chain investigator ZachXBT. Bitget's CEO and Elliptic attribute the heist to North Korea, and TRM Labs traced laundering through round-number wallet splits and cross-chain swap services including Thorchain, Across, Bridgers, Chainflip, and FixedFloat. Near Intents' SHIELD screening blocked over $50M in related swaps while Thorchain refused to selectively halt the attacker's addresses, spotlighting the gap between blockchain "permissionless" design and real-time sanctions/freeze response during active exchange-hack laundering.

ZcashTHORChain
ZachXBTTRM LabsElliptic+3

BlockchainΒ· Published and added 30 Sep 2026

arxiv.orgpaper🧠 AI

StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents

StateTape is a framework for long-horizon coding agents that replaces text-based context pruning/summarization with a symbol-level code graph tracking which code symbols each write could have affected. A per-write procedure uses the graph to nominate context records a write may have falsified, with a small manager model resolving ambiguous cases, turning staleness detection from text inference into an observation of actual code dependencies. The paper introduces TraceBench, a benchmark labeling what an agent holds versus what it actually needs, and shows improved resolve rates across six coding agents and three edit-heavy benchmarks with low computational overhead.

TraceBenchStateTape

coding-agents, researchΒ· Added 30 Sep 2026

orca.securityarticleπŸ›‘οΈ Security

Connect Orca’s ChatGPT Plugin: Cloud Risk Context in Chat and Codex

Orca Security's plugin connects ChatGPT and Codex to Orca's MCP server, letting security teams and developers query cloud alerts, attack paths, effective IAM permissions, and code-to-cloud origins directly from chat or a coding agent instead of logging into a console. The post walks through six security-team use cases (exposure discovery, CVE impact triage, alert-to-blast-radius investigation, identity permission review, CISO reporting) and three developer workflows in Codex where alerts are traced back to the Terraform/code that created the misconfiguration and fixed in place.

Model Context ProtocolOrca SecurityChatGPT+3
CVE-2025-55182

Cloud & InfraΒ· Added 2 Oct 2026, published 30 Sep 2026

coindesk.comarticleπŸ›‘οΈ Security

Bitget hackers move $4 million into Zcash’s private pool, making funds harder to trace

CoinDesk traces wallets linked to the Sept. 24 Bitget hack ($387.5M stolen) moving 2,746 ZEC (~$3.9M, ~15% of stolen ZEC) into Zcash's Ironwood shielded pool via two intermediary addresses, obscuring sender, recipient and amount once inside the pool. Blockchain investigator ZachXBT first flagged the transfers; separately, other attacker-linked proceeds were previously traced swapping ~$6.3M ether to bitcoin via THORChain despite the exchange's request to block the hacker. The piece illustrates real-world laundering tradecraft (privacy-pool deposits plus cross-chain DEX swaps) and the limits of on-chain tracing once funds enter a shielded pool.

ZcashTHORChainEthereum+1
Bitget hackZachXBTIronwood shielded pool

Blockchain, Threat IntelΒ· Published and added 30 Sep 2026

x.comthreadπŸ›‘οΈ Security

lee1981 (@lee1981b) on X

A detailed breakdown of CVE-2026-102710 (CVSS v4.0 9.3), a privilege-escalation flaw in Eclipse ThreadX RTOS builds with event tracing enabled: a module-supplied trace callback pointer is retained by the kernel and invoked with kernel privilege when the trace buffer wraps, letting an attacker who already controls a memory-protected user-mode module fault the kernel or execute code in kernel context. The thread walks through the vulnerable code path (registration, storage, invocation across the protection boundary), CWE-269/CWE-822 classification, affected versions (through v6.5.1.202602a_rel), and provides a defender hunting guide plus emergency remediation steps, noting no fixed upstream release or CISA KEV/EPSS entry exists yet.

Eclipse ThreadXCVSSNVD+1
CVE-2026-102710CWE-269CWE-822+1

Hardware & RF, Offensive Security, Blue Team & DetectionΒ· Published and added 30 Sep 2026

arxiv.orgpaperπŸ›‘οΈ Security

SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs

SparLeak is a side-channel attack exploiting a newly identified GPU micro-architectural leak, Sparsity-Induced Memory Access (SIMA), caused by input-dependent key-value cache access patterns in sparse attention mechanisms used for long-context LLM inference on shared GPUs. The attack recovers prefill-phase query attributes and reconstructs decoding-phase LLM responses by profiling token-level sparsity patterns from page-level memory observations, achieving 90.9% attribute-inference and 87.3% response-reconstruction success across three LLM architectures, three sparse-attention mechanisms, and three privacy-sensitive datasets. The authors release anonymized SIMA traces, trained attack models, and evaluation scripts/artifacts.

LLM
SparLeakSparsity-Induced Memory Access

AI Security, Hardware & RFΒ· Added 2 Oct 2026, published 30 Sep 2026

arxiv.orgpaper🧠 AI

TraceDance: Automated System for Building Agent Behavior Benchmarks from Real-World Deployment Traces

TraceDance is an automated system that mines real-world agent deployment traces to build targeted benchmarks for user-specified undesirable agent behaviors, using an Anchor-and-Confirm retrieval-plus-LLM-confirmation pipeline and an Anchor Synthesis Loop to generate behavior specifications. Benchmarks evaluate an LLM's next-turn response at a recorded decision point against a behavior-specific rubric, avoiding the need for reference answers or environment replay. Applied to 252,557 sessions in coding and tool-use domains, it produced 107 benchmarks with 4,125 instances, and testing nine frontier LLMs found a mean pass rate of only 26.7 percent, exposing persistent agentic behavior weaknesses.

TraceDance

evals, agentsΒ· Added 29 Sep 2026

Showing 150 of 278

Show more