Skip to content

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications.

Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson

VenueA*ICML
Year2024
ProceedingsICML

Browse the full ICML paper archive.