SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding ACL

Zhangchen Xu | Fengqing Jiang | Luyao Niu | Jinyuan Jia | Bill Yuchen Lin | Radha Poovendran |

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs ACL

Fengqing Jiang | Zhangchen Xu | Luyao Niu | Zhen Xiang | Bhaskar Ramasubramanian | Bo Li | Radha Poovendran |

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models EMNLP

Yuetai Li | Zhangchen Xu | Fengqing Jiang | Luyao Niu | Dinuka Sahabandu | Bhaskar Ramasubramanian | Radha Poovendran |