SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking.
Yingjie Xue, Xingyou Xia, Jun Zhang, Yunbo Cao, Dengpan Ye, Guotong Geng, Fei Li
Browse the full ACL paper archive.
Yingjie Xue, Xingyou Xia, Jun Zhang, Yunbo Cao, Dengpan Ye, Guotong Geng, Fei Li
Browse the full ACL paper archive.