The paper introduces an adaptive jailbreak attack framework that evaluates both cascaded pipelines and end‑to‑end large audio‑language models (LALMs) under a unified setting. It employs a feedback‑guided mutation engine to automatically generate and refine jailbreak candidates across textual prompts and audio perturbations, thereby broadening attack diversity. Experiments on six audio‑based systems show that both paradigms remain highly vulnerable, with the framework achieving higher attack success rates than existing methods.
By Linghan Huang, Bo Li, Huaming Chen, Kim-Kwang Raymond Choo
arXiv:2603. 19127v2 Announce Type: replace Abstract: As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface.
By Aravind Krishnan, Karolina Sta\'nczak, Dietrich Klakow
arXiv:2609.36849v1 Announce Type: cross
Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...
By Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang
arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.
By Yannick Assogba, Jacopo Cortellazzi, Javier Abad, Pau Rodriguez, Xavier Suau, Arno Blaas
arXiv:2508. 10031v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and ethical risks.
By Jinhwa Kim, Ian G. Harris
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.
By Qingjia Huang, Jingyu Zhang, Jianguo Wu, Yakai Li, Weijuan Zhang, Yankai Rong, Junyi Yao, Shengzhi Zhang, Xiaoqi Jia
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.
By Jiale Luo, Eric Han
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.
By Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena, Ziqian Zhong, Alexander Robey, Aditi Raghunathan
The paper introduces JMLLM, a multimodal jailbreaking approach that targets text, visual, and auditory inputs to expose vulnerabilities in large language models. It also presents TriJail, a new dataset containing jailbreak prompts across all three modalities. Experiments on TriJail and AdvBench show higher attack success rates and lower time overhead compared to existing methods.
By Yanxu Mao, Peipei Liu, Tiehan Cui, Zhaoteng Yan, Congying Liu, Datao You
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.
By Amit Levi, Rom Himelstein, Yaniv Nemcovsky, Avi Mendelson, Chaim Baskin
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...
By Aaditya Pratap, Harsh Kasyap, Somanath Tripathy
arXiv:2503.06989v5 Announce Type: replace-cross
Abstract: Recently, Multimodal Large Language Models (MLLMs) have demonstrated their superior ability in understanding multimodal content. However, the...
By Wenzhuo Xu, Zhipeng Wei, Xiongtao Sun, Zonghao Ying, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang, Quanchen Zou