How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs ACL

Yi Zeng | Hongpeng Lin | Jingwen Zhang | Diyi Yang | Ruoxi Jia | Weiyan Shi |

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models EMNLP

Yi Zeng | Weiyu Sun | Tran Huynh | Dawn Song | Bo Li | Ruoxi Jia |