Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
Authors: Yao Huang, Yitong Sun, Shouwei Ruan, Yichi Zhang, Yinpeng Dong, Xingxing Wei | Published: 2025-05-27
LLMの安全機構の解除
Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models
Authors: Junjie Xiong, Changjia Zhu, Shuhang Lin, Chong Zhang, Yongfeng Zhang, Yao Liu, Lingyao Li | Published: 2025-05-22
When Safety Detectors Aren’t Enough: A Stealthy and Effective Jailbreak Attack on LLMs via Steganographic Techniques
Authors: Jianing Geng, Biao Yi, Zekun Fei, Tongxi Wu, Lihai Nie, Zheli Liu | Published: 2025-05-22
Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
Authors: Jiawen Wang, Pritha Gupta, Ivan Habernal, Eyke Hüllermeier | Published: 2025-05-20
Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion
Authors: Tiehan Cui, Yanxu Mao, Peipei Liu, Congying Liu, Datao You | Published: 2025-05-20
PandaGuard: Systematic Evaluation of LLM Safety in the Era of Jailbreaking Attacks
Authors: Guobin Shen, Dongcheng Zhao, Linghao Feng, Xiang He, Jihang Wang, Sicheng Shen, Haibo Tong, Yiting Dong, Jindong Li, Xiang Zheng, Yi Zeng | Published: 2025-05-20
JULI: Jailbreak Large Language Models by Self-Introspection
Authors: Jesson Wang, Zhanhao Hu, David Wagner | Published: 2025-05-17 | Updated: 2025-05-20
Dark LLMs: The Growing Threat of Unaligned AI Models
Authors: Michael Fire, Yitzhak Elbazis, Adi Wasenstein, Lior Rokach | Published: 2025-05-15
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
Authors: Yidan Wang, Yanan Cao, Yubing Ren, Fang Fang, Zheng Lin, Binxing Fang | Published: 2025-05-15
One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models
Authors: Haoran Gu, Handing Wang, Yi Mei, Mengjie Zhang, Yaochu Jin | Published: 2025-05-12