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

Boyi Wei et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.05162

access: open

type: Informal or Other Publication

metadata version: 2024-05-07

a service of  Schloss Dagstuhl - Leibniz Center for Informatics