Skip to content

83 results for “Jailbreak”

ListGrid
What you seeeverything
RecentOldestAddedA–Z
All types83Repos22Papers21Articles18Write-ups12Advisories4
Threads3Tools2Talks1
“Jailbreak”
deploymentsafety.openai.compaper🛡️ Security

GPT-Rosalind-6 System Card Addendum

GPT-Rosalind-6 System Card Addendum is OpenAI's safety documentation for a life-sciences model that shares weights with GPT-6 Astra. It rates the model High in Biological and Chemical and Critical in Cybersecurity under the Preparedness Framework. It reports biology evaluations, trusted-access controls, biosecurity refusal pass rates, a historical cyber jailbreak regression (14.3% task success), and sabotage and monitor-evasion results.

GPT-Rosalind-6GPT-6 AstraOpenAI
Preparedness FrameworkGPT-Rosalind-5.5ExploitBench+5

AI Security, GRC· Published and added 30 Oct 2026

deploymentsafety.openai.compaper🧠 AI

GPT-Rosalind-6 System Card Addendum

GPT-Rosalind-6 System Card Addendum describes OpenAI's life-sciences reasoning model, which uses the same weights as GPT-6 Astra and is offered only through trusted access. It reports life-science benchmark gains over GPT-Rosalind-5.5 (MedChemBench v7 49.6% vs 28.9%), High-capability Biological and Chemical Preparedness results, and below-threshold Critical bio design evaluations. It also covers access controls, refusal evaluations, cyber jailbreak regression and alignment tables.

GPT-6 AstraGPT-Rosalind-6GPT-Rosalind-5.5
OpenAIPreparedness FrameworkMedChemBench v7+16

ai-safety, evals, models· Published and added 30 Oct 2026

x.compaper🛡️ Security

Cryptography and Security Papers (@FSFG) on X

PrivacyEvalClaw is a tool-augmented deliberative agent that audits privacy leakage in LLM jailbreak responses. The paper is by Krishna Kanth Nakka and co-authors, and it was accepted to AACL-IJCNLP 2026 (arXiv 2610.36711, cs.CR). The tweet gives only the title, authors and venue, so the method and results are not described.

LLM
PrivacyEvalClaw

AI Security· Added 30 Oct 2026, published 29 Oct 2026

x.compaper🧠 AI

Cryptography and Security Papers (@FSFG) on X

PrivacyEvalClaw is a tool-augmented deliberative agent for auditing privacy leakage in LLM responses produced under jailbreak prompts. By Krishna Kanth Nakka and five co-authors, the paper is on arXiv (cs.CR) and accepted to AACL-IJCNLP 2026. The fetched post gives only the title, authors and venue, so method details and results are not available here.

LLM
PrivacyEvalClawKrishna Kanth NakkaAACL-IJCNLP 2026+1

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

deploymentsafety.openai.compaper🛡️ Security

Addendum to GPT-6 Luna System Card: October 28, 2026 Update

Addendum to the GPT-6 Luna system card for the model update of 29 October 2026 (the title says October 28). OpenAI keeps the High rating for cybersecurity and biological/chemical capability under its Preparedness Framework. It reports ExploitBench 46.19% and SEC-Bench Pro 51.75% (GPT-6 Astra: 85.4%), higher multiturn jailbreak defender success than the October 7 version, and GPT-Red prompt-injection results. It also reports weaker factuality and dual-use biology refusal.

GPT-6 LunaGPT-6 AstraOpenAI+1
Preparedness FrameworkGPT-RedExploitBench+4

AI Security· Published and added 29 Oct 2026

deploymentsafety.openai.comarticle🧠 AI

Addendum to GPT-6 Luna System Card: October 28, 2026 Update

The addendum to the GPT-6 Luna system card covers the October 29, 2026 update of GPT-6 Luna, which gives more concise answers and less agreeable language. It compares the update with GPT-6 Luna (October 7) on safe completions, under-18 evals, jailbreaks, HealthBench, MentalHealthBench, hallucination and alignment. OpenAI keeps its High rating for cybersecurity and for biological and chemical capability. Hallucination error rates rose, and HealthBench scores fell.

ChatGPT
OpenAIGPT-6 LunaGPT-6 Sol+10

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

deploymentsafety.openai.compaper🛡️ Security

Addendum to GPT-6 Astra System Card: GPT-6.1 Terra

Addendum to the GPT-6 Astra system card for OpenAI's GPT-6.1 Terra, rated Critical in cybersecurity and High in biological and chemical capability under the Preparedness Framework. It reports multiturn jailbreak and prompt-injection results, alignment tests (auto-review circumvention, ExploitGym honeypot, monitor evasion), and cyber scores: 97.10% ExploitBench, 24.5% on the internal recent-vulnerability port, 5 of 22 Sandbox Bench targets.

GPT-6.1 TerraGPT-6 AstraOpenAI+1
Preparedness FrameworkExploitGymExploitBench+11

AI Security· Published and added 26 Oct 2026

deploymentsafety.openai.comarticle🧠 AI

Addendum to GPT-6 Astra System Card: GPT-6.1 Terra

GPT-6.1 Terra system card addendum from OpenAI, covering a fast, efficient model in the GPT-6 series. It reports safe-completion, jailbreak, HealthBench, MentalHealthBench, hallucination, alignment and monitorability results against GPT-5.6 Terra and GPT-6.1 Sol. OpenAI rates it Critical in cybersecurity and High in biological and chemical capability, with the same safeguards stack as GPT-6 Astra.

CodexHugging Face
OpenAIGPT-6.1 TerraGPT-6 Astra+16

ai-safety, evals, models· Published and added 26 Oct 2026

arxiv.orgpaper🛡️ Security

SentryBench: A Cost-Sensitive Benchmark for Adversarial Robustness of Tool-Using LLM Agents in Public-Safety Deployments

SentryBench is a benchmark for tool-using LLM agents in public-safety settings (public alerts, responder dispatch, citizen-record queries). It scores attack success, over-refusal and over-reaction on a cost-sensitive frontier, using real emergency-call transcripts and real injection/jailbreak payloads. Across 840 episodes on three frontier models and three defenses, refuse-more caution raised over-refusal to 100 percent on two models, while a trust-gating wrapper gave the lowest harm on every model.

LLM
SentryBenchover-refusalover-reaction+1

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

arxiv.orgpaper🧠 AI

Task Format as a Factor in Adaptation: A Controlled Comparison of LoRA and Full Fine-Tuning for Prompt-Safety Classification

This paper compares LoRA and full fine-tuning for prompt-safety classification using a matched 400M encoder-decoder pair (Ettin) across three task formats, with up to 15 seeds per cell and pre-specified analyses. Full fine-tuning leads LoRA by 2-3 pp at the pre-specified learning rates, and the encoder gap closes when both use the same learning-rate search. Training LoRA to write a reason after its verdict adds 4.0 pp, while a content-free sentence of equal length does not. Trained models beat a prompted 8B in domain but trail it by 8-23 pp on adversarial jailbreaks and over-flag benign prompts (27-66% against 2-3%).

LoRAEttinTransformer

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

x.comthread🛡️ Security

Techjunkie Aman (@Techjunkie_Aman) on X

ns2jb is a software-only jailbreak for the Nintendo Switch 2 running firmware 23.0.1, announced in a post on X. It runs arbitrary native code, allows save dumping, reverse engineering and game modding, and reaches most peripherals via MMIO. It is tethered (rerun after reboot) and gives no CFW or full kernel control. The post says Mario Kart World has been modded with custom characters. It gives no technical detail on the exploit chain.

Nintendo Switch 2
ns2jbNintendoMario Kart World

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

arxiv.orgpaper🛡️ Security

Concerns in Benchmarking Jailbreaks: An Empirical Study of Attack Success Rates

This arXiv paper tests eight jailbreak attacks against three open-weight language models under three evaluation procedures. Low-resource language attacks score 96.0% mean ASR under keyword matching but 2.7% under a Qwen3 judge using StrongREJECT instructions. At Ollama's default temperature of 0.8, 100 samples of an unchanged request give 100% ASR by keywords and 50% by the judge. The authors recommend explicit success definitions, matched response budgets, validated evaluators and cumulative-failure reporting.

OllamaQwenLLM
StrongREJECTDeepInceptionattack success rate+1

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

arxiv.orgpaper🧠 AI

Concerns in Benchmarking Jailbreaks: An Empirical Study of Attack Success Rates

Concerns in Benchmarking Jailbreaks is an October 2026 arXiv study of eight jailbreak attacks on three open-weight models under three evaluation procedures. Low-resource language attacks score 96.0% ASR by keyword matching but 2.7% under a Qwen3 evaluator using StrongREJECT instructions. Attack rankings flip with attempt budgets, and 100 samples at Ollama's default temperature 0.8 give 100% ASR by keywords, 50% by the evaluator.

OllamaQwen3LLM
StrongREJECTDeepInceptionarXiv

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

decrypt.coarticle🛡️ Security

Hackers Jailbreak iPhone 18 Pro on Stage, and It Survives a Reboot

Reports that Calif.io demonstrated an untethered jailbreak of an iPhone 18 Pro on iOS 27.0.1 at Hexacon in Paris, showing root SSH access after a reboot and passcode unlock. The vulnerabilities are unnamed and no tool is public; Calif says it will publish later. The article notes Calif's prior use of Claude and Mythos Preview for exploit development, Apple's iOS 27 notes crediting Calif for two unrelated crash bugs, and the Apple mitigations (sandbox, PAC, secure boot chain) such a chain must defeat.

iOSiPhoneClaude+2
CalifHexaconBilly Ellis+4

Mobile Security, Offensive Security· Published and added 16 Oct 2026

deepmind.googlearticle🧠 AI

Gemini 4 Argon: Built to solve your hardest problems

Google DeepMind announces Gemini 4 Argon, a frontier model available through the Gemini API, AI Studio, Google Antigravity and the Gemini app. Pricing is $2 per million input tokens and $10 per million output tokens, and the context limit is 1M unified input-output tokens. It reports #1 on the Vals Index, 87% on ERQA and 0.7% attack success on Gray Swan IPI. Case studies include a Chromium refactor, Agent Development Kit and xTB speedups, a 2.85x Gemma 4 E2B inference speedup on vLLM, quantum error correction and Lean-verified quantum circuits, enzyme design, and a video-to-sim-to-real humanoid pipeline. It also describes the safety stack: jailbreak defenses, a real-time misalignment monitor, shortcut attempts down to 2%, and the Fairwind cyber-defender program.

GeminiGoogle AntigravityGoogle AI Studio+4
Gemini 4 ArgonGoogle DeepMindGoogle+16

models, coding-agents, ai-safety· Published and added 13 Oct 2026

adversa.aiarticle🛡️ Security

Top GenAI security resources — October 2026

Adversa AI's October 2026 roundup of 38 GenAI security resources, grouped into attack techniques, defenses, red teaming, vulnerabilities, incidents, articles and frameworks. Highlights include Anthropic's finding that GLM-5.3 safeguards collapse under prefill and abliteration, capability laundering and activation-dilution jailbreaks, RAG poisoning attacks, the LiteLLM proxy flaw (CVE-2026-35029), and the SGLang pickle RCE (CVE-2026-86793). It also covers a joint US advisory on industrial-scale model distillation. It closes with advice to assume model safeguards can be removed and to harden the serving stack around the model.

LLMLiteLLMSGLang+3
CVE-2026-35029CVE-2026-86793GLM-5.3+14

AI Security· Published and added 13 Oct 2026

arxiv.orgpaper🛡️ Security

ReSI: Recursive Safety Improvement toward Resistant and Resilient AI

ReSI is a recursive safety improvement framework. Each round runs diverse red-teaming methods against the current target model, develops training recipes for the vulnerabilities found, and promotes the update with the largest safety gain among those passing a Pareto gate on capability retention. Across four dense and mixture-of-experts models it cuts mean X-Teaming multi-turn jailbreak attack success from 86.01% to 31.45%, versus 56.69% for the best frontier model evaluated (GPT-5.6-Luna). It also beats alignment baselines on nearly all safety evaluations while largely preserving general capability. It frames the goals as resistance to known threats and resilience to unforeseen ones, following R²AI.

LLM
X-TeamingR2AIGPT-5.6-Luna

AI Security· Added 9 Oct 2026, published 8 Oct 2026

arxiv.orgpaper🛡️ Security

BRANCH: Bypassing Multi-Scanner AI Guardrails

BRANCH is a bypass methodology for guardrail systems built from multiple scanners (prompt injection/jailbreak detectors). It uses a branching tree search that applies adversarial perturbations to individual scanners and selects techniques based on overall improvement across all scanners, decoupling bypass evaluation from attack signal optimization. It reports 100% attack success across 6 guardrail systems in 120 scenarios with 72% fewer queries and 4.5x lower wallclock time than established techniques, and transfers to 29 unseen guardrails, including 8 commercial black-box ones.

LLM
BRANCH

AI Security· Added 9 Oct 2026, published 7 Oct 2026

deploymentsafety.openai.comadvisory🧠 AI

GPT-6 Sol and GPT-6 Luna: October 2026 update

OpenAI's system card accompanying the October 2026 ChatGPT rollout of GPT-6 Sol and GPT-6 Luna, replacing GPT-5.6 Sol and Luna for free and paid users (Codex and ChatGPT Work retain the September versions). It details Preparedness Framework results (High capability in Cybersecurity and Biological/Chemical domains, below High in AI Self-Improvement), multiturn jailbreak and GPT-Red prompt-injection robustness, alignment evaluations on respecting Auto-review/warnings and deceptive disclosure, hallucination rates, and health/mental-health benchmarks (HealthBench, HealthBench Professional, MentalHealthBench), alongside some noted regressions in self-harm, sexual content, gore and teen (U18) safety categories.

ChatGPTCodexOpenAI API
GPT-6 SolGPT-6 LunaGPT-5.6 Sol+11

ai-safety, evals, models· Published and added 7 Oct 2026

deploymentsafety.openai.comarticle🛡️ Security

GPT-6 Sol and GPT-6 Luna: October 2026 update

OpenAI's system card for the October 2026 GPT-6 Sol and GPT-6 Luna release in ChatGPT, detailing safety and preparedness evaluations under the Preparedness Framework. It reports High-capability classifications in Cybersecurity (ExploitBench: 82.62%/44.66%, SEC-Bench Pro: 68.85%/48.50%) and Biological/Chemical domains (below Critical thresholds), multi-turn jailbreak robustness results, GPT-Red direct/indirect prompt-injection robustness (99.99%/99.79%), and alignment evaluations covering Auto-review circumvention, warning-bypass behavior, and blocker/search-tool deception, alongside HealthBench, MentalHealthBench and hallucination benchmarks.

ChatGPTCodexOpenAI+1
GPT-6 SolGPT-6 LunaGPT-5.6 Sol+10

AI Security· Published and added 7 Oct 2026

arxiv.orgpaper🛡️ 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 Security· Added 7 Oct 2026, published 6 Oct 2026

arxiv.orgpaper🛡️ Security

CorrectGuard: Eyes-Off Correctness Estimation for Black-Box Security Guardrails

CorrectGuard is a framework for estimating whether black-box AI security guardrails made correct decisions on inputs that are inaccessible to humans (production privacy) or to the guardrail-auditing model itself, using only labeled "eyes-on" data and no internal access to the guardrail. The authors test in-context-learning, embedding, and finetuning-based correctness classifiers across 13 safety/security datasets (harmful content, jailbreaks, prompt injection, extraction) and multiple open-weight guardrails, showing up to 25-point macro-accuracy gains in error identification and improved risk-based abstention/ranking of guardrail decisions.

LLM

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

arxiv.orgpaper🧠 AI

CorrectGuard: Eyes-Off Correctness Estimation for Black-Box Security Guardrails

CorrectGuard is a framework for estimating how accurately black-box security guardrails (jailbreak, harmful-content, prompt-injection and extraction detectors) perform on inputs that cannot be inspected by humans or by the evaluating model itself, using an independent correctness model trained only on labeled "eyes-on" data. The authors test in-context-learning, embedding-based, and fine-tuned correctness classifiers under leave-one-dataset-out evaluation across 13 safety/security datasets and multiple open-weight guardrails, showing up to 25-point macro-accuracy gains and improved risk-coverage tradeoffs (AURC reduced from 0.33–0.44 to 0.17–0.22) for guardrail decision ranking and abstention. The work matters for anyone building auditing or eval pipelines for opaque safety classifiers without privileged access to their internals.

CorrectGuard

evals, research· Added 5 Oct 2026, published 2 Oct 2026

github.comrepo🛡️ Security

AI-Infra-Guard (A.I.G) — Tencent Zhuque Lab

AI-Infra-Guard (A.I.G) is Tencent Zhuque Lab's open-source AI red-teaming platform combining AI infrastructure vulnerability scanning (2000+ CVE rules covering vLLM, llama.cpp, LangFlow, n8n, MLflow and 145+ other AI components), MCP server/skill security scanning, LLM API poisoning detection, and multi-turn jailbreak evaluation (Many-Shot, PAIR, GOAT, ActorAttack). It ships CLI tools (skill-scan, mcp-scan, agent-scan), a Docker-deployed web UI, and has produced original research including FORGE-Bench (loss-of-control benchmark), RogueHandoff-20, and SkillJack (persistent skill backdoors), with talks at Black Hat Europe 2025 on MCP security.

Model Context ProtocolDockervLLM+3
SkillTrustBenchFORGE-BenchRogueHandoff-20+2

AI Security, Offensive Security· Added 30 Sep 2026

x.comthread🛡️ Security

steve hsu (@hsu_steve) on X

Tweet relaying Anthropic's finding that GLM-5.3 is "the most cyber-capable open-weight model released to date," trailing the US frontier by roughly four months on an aggregate of CAISI's cyber benchmarks. It also cites a 64-100% jailbreak success rate against the model's safeguards, with the poster arguing this favors faster-deploying defenders over attackers.

GLMAnthropic
GLM-5.3CAISI

AI Security· Published and added 30 Sep 2026

x.comthread🧠 AI

steve hsu (@hsu_steve) on X

A tweet reporting that GLM-5.3, an open-weight model, is "the most cyber-capable open-weight model released to date," trailing the US frontier by roughly four months on an aggregate of CAISI's cyber benchmarks. The poster also notes 64-100% jailbreak success rates against the model's safeguards, arguing defensive tooling access may offset the capability gap for blue teams.

GLM-5.3CAISI

evals, ai-safety· Published and added 30 Sep 2026

decrypt.coarticle🛡️ Security

Someone Finally Jailbroke the PS5—Just After Sony Said Players Don’t Own Their Games

Decrypt reports on Relapse, a newly public tethered PS5 jailbreak covering firmware 7.00–13.60, delivered by pointing the console's DNS at an attacker-controlled server and loading a crafted page through the built-in User Guide's WebKit browser, then chaining into a kernel-stage exploit and ELF loader to run homebrew and game backups. The MIT-licensed exploit code is on GitHub; it is non-persistent (must be rerun after every reboot) and does not work on the September 16 firmware 14.00 update. The article frames it against Sony's concurrent court argument that "Buy Now" digital purchases don't confer real game ownership.

PlayStation 5WebKit
RelapseNathan FargoApolloHB

Hardware & RF, Offensive Security· Added 30 Sep 2026, published 29 Sep 2026

github.comrepo🛡️ Security

garak v0.17.0 — LLM vulnerability scanner release

Release notes for garak v0.17.0, NVIDIA's open-source LLM vulnerability scanner used for red-teaming and probing models for jailbreaks, prompt injection, data leakage and other failure modes. The release adds an EU AI Act risk-category mapping to tag and group probe results, plus fixes to detectors (agent_breaker judge verdict validation, packagehallucination import parsing, MarkdownExfilContent divide-by-zero, TriggerListDetector alignment) and probes (badchars ASCII selection, Markdown exfiltration link templates), along with Ollama generator improvements and dropped Python 3.10 support in favor of 3.13.

OllamaPython
EU AI ActAgentBreakerIntentProbe+2

AI Security· Added 29 Sep 2026

deploymentsafety.openai.comarticle🛡️ Security

Addendum to GPT-6 Astra System Card: GPT-6.1 Sol

OpenAI system card addendum for GPT-6.1 Sol reports Preparedness Framework results rating the model Critical capability in cybersecurity and High in biological and chemical risk, reusing GPT-6 Astra safeguards stack. It details jailbreak (static and multiturn) and indirect prompt-injection defender success rates, ExploitBench, ExploitGym and SEC-Bench Pro cyber-capability scores, and chain-of-thought monitor-evasion experiments showing the model rarely succeeds at hiding misaligned reasoning from full-context monitors, plus honeypot-exploitation and sabotage-evasion tests.

OpenAICodexGPT-5.5
GPT-6.1 SolGPT-6 AstraGPT-6 Sol+11

AI Security· Added 7 Oct 2026, published 29 Sep 2026

deploymentsafety.openai.comadvisory🧠 AI

Addendum to GPT-6 Astra System Card: GPT-6.1 Sol

OpenAI's system card addendum for GPT-6.1 Sol, a fast and affordable model in the GPT-6 family with capabilities comparable to GPT-6 Astra, reports Preparedness Framework determinations (Critical cybersecurity, High biological and chemical capability, sub-High AI self-improvement) and the same safeguards stack as Astra. It details extensive safety and alignment evaluations including safe-completion benchmarks, jailbreak and prompt-injection robustness, HealthBench and MentalHealthBench scores, deceptive-behavior and monitor-evasion tests, and chain-of-thought monitorability and controllability results, comparing GPT-6.1 Sol against GPT-6 Astra, GPT-6 Sol, GPT-6 Luna, and the GPT-5.6 series.

Codex
GPT-6.1 SolGPT-6 AstraGPT-6 Sol+17

ai-safety, evals· Added 7 Oct 2026, published 29 Sep 2026

Showing 30 of 83

Show more