COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.
Xingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin, Bin Hu
Browse the full ICML paper archive.
Xingang Guo, Fangxu Yu, Huan Zhang, Lianhui Qin, Bin Hu
Browse the full ICML paper archive.