Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
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
Published: 01 Jan 2024, Last Modified: 13 Nov 2024
ICML 2024
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Loading