"Refusing Safe Prompts for Multi-modal Large Language Models."

Zedian Shao et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2407.09050

access: open

type: Informal or Other Publication

metadata version: 2024-08-16

a service of  Schloss Dagstuhl - Leibniz Center for Informatics