Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Open Webpage

Biao Yi, Tiansheng Huang, Sishuo Chen, Tong Li, Zheli Liu, Zhixuan Chu, Yiming Li

Published: 01 Jan 2025, Last Modified: 16 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0