CHASE: Contextual History for Adaptive and Simple Exploitation in Large Language Model Jailbreaking.

Zhiqiang Hao, Chuanyi Li, Ye Fan, Jun Cai, Xiao Fu, Shangqi Wang, Hao Shen, Jiao Yin, Jidong Ge, Bin Luo, Vincent Ng

Browse the full AAAI paper archive.