ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs.
Hao Di, Tong He, Haishan Ye, Yinghui Huang, Xiangyu Chang, Guang Dai, Ivor W. Tsang
Browse the full ICLR paper archive.
Hao Di, Tong He, Haishan Ye, Yinghui Huang, Xiangyu Chang, Guang Dai, Ivor W. Tsang
Browse the full ICLR paper archive.