"Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts."

Yuanwei Wu et al. (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.09127

access: open

type: Informal or Other Publication

metadata version: 2023-11-21

a service of  Schloss Dagstuhl - Leibniz Center for Informatics