大模型对齐与安全

MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation

Weisen Jiang, Sinno Jialin Pan

专题命中 越狱攻击 ：jailbreak(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted By NeurIPS 2025

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates

Hyunjun Kim, Junwoo Ha, Sangyoon Yu, Haon Park

机构 * AIM Intelligence（AIM智能） 纠错

专题命中 越狱攻击 ：jailbreak(title)；分类 cs.CL、cs.AI

Comments NeurIPS 2025 Workshop on Lock-LLM

Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach

Xiangfang Li, Yu Wang, Bo Li

专题命中 越狱攻击 ：safety(abstract)；jailbreak(abstract)

$\textit{Agents Under Siege}$: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks

Rana Muhammad Shahroz Khan, Zhen Tan, Sukwon Yun, Charles Fleming, Tianlong Chen

机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校） ； Arizona State University（亚利桑那州立大学） ； Cisco（思科） 纠错

专题命中 越狱攻击 ：safety(abstract)；分类 cs.CL、cs.AI、cs.LG

PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization

Aofan Liu, Lulu Tang, Ting Pan, Yuguo Yin, Bin Wang, Ao Yang

机构 * School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院） ； School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

专题命中 越狱攻击 ：jailbreak(abstract)；分类 cs.AI

Comments Accepted to IEEE International Conference on Multimedia and Expo (ICME) 2025