UMD: Unsupervised Model Detection for X2X Backdoor Attacks by Xiang, Zhen, Xiong, Zidi, Li, Bo

Get full text

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content by Yuan, Zhuowen, Xiong, Zidi, Zeng, Yi, Yu, Ning, Jia, Ruoxi, Song, Dawn, Li, Bo

Get full text

Under-confidence Backdoors Are Resilient and Stealthy Backdoors by Peng, Minlong, Xiong, Zidi, Nguyen, Quang H, Sun, Mingming, Doan, Khoa D, Li, Ping

Get full text

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models by Xiang, Zhen, Jiang, Fengqing, Xiong, Zidi, Ramasubramanian, Bhaskar, Poovendran, Radha, Li, Bo

Get full text

GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning by Xiang, Zhen, Zheng, Linzhi, Li, Yanjie, Hong, Junyuan, Li, Qinbin, Xie, Han, Zhang, Jiawei, Xiong, Zidi, Xie, Chulin, Yang, Carl, Song, Dawn, Li, Bo

Get full text

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models by Wang, Boxin, Chen, Weixin, Pei, Hengzhi, Xie, Chulin, Kang, Mintong, Zhang, Chenhui, Xu, Chejian, Xiong, Zidi, Dutta, Ritik, Schaeffer, Rylan, Truong, Sang T, Arora, Simran, Mantas Mazeika, Hendrycks, Dan, Lin, Zinan, Cheng, Yu, Koyejo, Sanmi, Song, Dawn, Li, Bo

Get full text