AI RESEARCH
VERA: Variational Inference Framework for Jailbreaking Large Language Models
arXiv CS.LG
•
ArXi:2506.22666v3 Announce Type: replace-cross The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings. Without a principled objective for gradient-based optimization, most existing approaches rely on genetic algorithms, which are limited by their initialization and dependence on manually curated prompt pools. Furthermore, these methods require individual optimization for each prompt, failing to provide a comprehensive characterization of model vulnerabilities.