arXiv:2602. 24009v4 Announce Type: replace-cross Abstract: Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols.
arXiv:2607. 19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates.
The paper evaluates six automated jailbreak evaluators—HarmBench, JailbreakBench, JailbreakRadar, StrongReject, JADES, and JailMeter—using human-labeled data from JailbreakQR and JailMeter-Eva. It measures each evaluator’s agreement with human judgments, error types, and consistency across attack families, controlling for model-specific variation by using a shared LLM judge where needed. The study finds that JADES performs best overall, with HarmBench and StrongReject also showing strong performance.
The paper introduces Fair-ASR, a protocol for evaluating black‑box jailbreak attacks using a shared target‑call budget, addressing the bias of prior studies that rely solely on attack success rate. Re‑evaluating 11 attacks under this protocol shows significant shifts in rankings and highlights that many methods are not efficient in both target and attacker calls. The authors then present ReCode, a budget‑efficient attack that combines desensitization rewriting with low‑cost primitives, achieving 85% ASR on GPT‑5 with only 7.19 attacker calls per request under a 20‑target‑call budget.
The paper presents a systematic study of combining defenses against jailbreak attacks on Large Language Models across different pipeline stages. It introduces a standardized evaluation framework that defines attack-success-rate, controls query budgets, and applies explicit fairness rules. Across 19 attacks and 15 defenses, the study finds that no single defense dominates, but carefully selected combinations can provide strong safety with minimal loss of utility, offering practical guidance for layered defense pipelines.
arXiv:2510. 01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings.
arXiv:2606. 11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries.
The paper introduces Fair-ASR, a new evaluation protocol for black-box jailbreak attacks that uses shared target-call budgets to provide a fair comparison across methods. Re‑evaluating 11 attacks under this protocol shows that rankings shift significantly with different budgets, and that simple perturbations and templates remain competitive. The authors also present ReCode, a budget‑efficient attack that combines desensitization rewriting with low‑cost primitives, achieving 85% ASR on GPT‑5 with only 7.19 attacker calls per request under a 20‑call budget.
The paper introduces a self‑evolving defense framework for large language models that uses a persistent, cross‑interaction rule memory to adapt to new jailbreak attacks. When an attack succeeds, the system abstracts the failure into a method‑level rule that captures the structural attack wrapper, allowing the rule to generalize across an entire attack family. This memory‑based adaptation operates without parameter updates, works with both open‑weight and black‑box models, and has been shown to reduce attack success rates while preserving benign utility across multiple jailbreak families.
arXiv:2608.21895v1 Announce Type: cross Abstract: Locally deployed Large Language Models (LLMs) via inference engines such as Ollama run without the moderation and abuse detection present in API-serv...
The paper "Jailbreaking in the Haystack" introduces NINJA, a jailbreak technique that exploits long-context language models by appending benign, model-generated content to harmful user goals. It demonstrates that the position of harmful goals within the context is crucial for safety, and shows that NINJA significantly boosts attack success rates on models such as LLaMA, Qwen, Mistral, and Gemini. Unlike previous methods, NINJA is low-resource, transferable, less detectable, and compute‑optimal, revealing that carefully crafted benign long contexts can expose fundamental vulnerabilities in modern LMs.
arXiv:2608. 03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much protection these safeguards provide, or how consistently across developers.
arXiv:2502. 09755v4 Announce Type: replace-cross Abstract: Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space.