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.
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.
MLCommons Jailbreak Benchmark v1.0 is a new methodology for assessing how well large language models resist single‑turn, text‑based jailbreak attacks. It evaluates eight open‑weight systems with 264 seed prompts across eleven hazard categories, using the AILuminate Assessment Standard v1.4 to measure the Resilience Gap—the difference in safety performance between baseline and adversarial conditions. The benchmark found that unsafe‑response rates rose from 11.08% to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57% and highlighting variability in attack effectiveness and evaluator reliability.
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.
The study shows that jailbreak robustness in language models is highly sensitive to operational-state changes. Even minor alterations to system prompts, not intended to affect safety, can dramatically shift attack success rates across seven aligned models and three jailbreak methods. The authors link these variations to changes in hidden representations along a refusal-related axis, which can predict jailbreak outcomes.
AlcaTRAz is a prompt‑level defense that uses rule trees to insert controlled character‑level perturbations into input text, disrupting jailbreak attacks without modifying or retraining the target LLM. It operates solely on the input, making it suitable for black‑box deployments, and was evaluated on 33 open‑weight models and 22 jailbreak types, outperforming three baseline defenses in 73.4 % of model‑attack combinations. While it significantly reduces high‑severity jailbreak success, it does not eliminate it and is intended as one layer of a broader defense strategy.
arXiv:2502.16903v3 Announce Type: replace Abstract: Despite the growing interest in jailbreaks as an effective red-teaming tool for building safe and responsible large language models (LLMs), flawed...
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.
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. We introduce the FAR.
arXiv:2510. 15476v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security failures a practical concern.
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.
The paper introduces a new metric, ASR_STEP, that extends the traditional attack success rate (ASR) by penalizing repeated calls to a victim large language model during jailbreak attempts. Experiments on JailBreakBench show that GCG’s scores drop by 7.0–8.7 percentage points after discounting, while PAP’s scores remain unchanged, and PAIR’s discount ranges from 3.4–12 percentage points depending on the iterative strategy. The authors argue that reporting both ASR and ASR_STEP makes the cost of repeated victim-model interactions explicit.
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...