JAIL: Adaptive multi-turn jailbreak attacks reveal limitations of LLM safety alignment

Yunhao Feng, Mingrui Lao, Jun Wang, Yishan Li, Xiaolong Li, Yuxiang Xie, Yanming Guo. JAIL: Adaptive multi-turn jailbreak attacks reveal limitations of LLM safety alignment. Expert Syst. Appl., 333:133684, 2027. [doi]

Abstract

Abstract is missing.