Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation
Authors: Junbo Zhang, Ran Chen, Qianli Zhou, Xinyang Deng, Wen Jiang | Published: 2025-11-24
Disabling Safety Mechanisms of LLM
Black-Box Guardrail Reverse-engineering Attack
Authors: Hongwei Yao, Yun Xia, Shuo Shao, Haoran Shi, Tong Qiao, Cong Wang | Published: 2025-11-06
Death by a Thousand Prompts: Open Model Vulnerability Analysis
Authors: Amy Chang, Nicholas Conley, Harish Santhanalakshmi Ganesan, Adam Swanda | Published: 2025-11-05
Multimodal Safety Is Asymmetric: Cross-Modal Exploits Unlock Black-Box MLLMs Jailbreaks
Authors: Xinkai Wang, Beibei Li, Zerui Shao, Ao Liu, Shouling Ji | Published: 2025-10-20
Proactive defense against LLM Jailbreak
Authors: Weiliang Zhao, Jinjun Peng, Daniel Ben-Levi, Zhou Yu, Junfeng Yang | Published: 2025-10-06
LLM Watermark Evasion via Bias Inversion
Authors: Jeongyeon Hwang, Sangdon Park, Jungseul Ok | Published: 2025-09-27 | Updated: 2025-10-01
Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Authors: Miao Yu, Zhenhong Zhou, Moayad Aloqaily, Kun Wang, Biwei Huang, Stephen Wang, Yueming Jin, Qingsong Wen | Published: 2025-09-26 | Updated: 2025-09-30
RLCracker: Exposing the Vulnerability of LLM Watermarks with Adaptive RL Attacks
Authors: Hanbo Huang, Yiran Zhang, Hao Zheng, Xuan Gong, Yihan Li, Lin Liu, Shiyu Liang | Published: 2025-09-25
bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
Authors: Wence Ji, Jiancan Wu, Aiying Li, Shuyi Zhang, Junkang Wu, An Zhang, Xiang Wang, Xiangnan He | Published: 2025-09-24
Send to which account? Evaluation of an LLM-based Scambaiting System
Authors: Hossein Siadati, Haadi Jafarian, Sima Jafarikhah | Published: 2025-09-10