PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning NAACL

Tianrong Zhang | Zhaohan Xi | Ting Wang | Prasenjit Mitra | Jinghui Chen |

Jailbreak Open-Sourced Large Language Models via Enforced Decoding ACL

Hangfan Zhang | Zhimeng Guo | Huaisheng Zhu | Bochuan Cao | Lu Lin | Jinyuan Jia | Jinghui Chen | Dinghao Wu |

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections NAACL

Yuanpu Cao | Bochuan Cao | Jinghui Chen |

Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM ACL

Bochuan Cao | Yuanpu Cao | Lu Lin | Jinghui Chen |