Jan 03, 2025Ravie LakshmananMachine Learning / Vulnerability Cybersecurity researchers have shed light on a new jailbreak technique that could be used to get past a large language model's (LLM) safety guardrails and produce potentially harmful or malicious responses. The multi-turn (aka many-shot) attack strategy has been codenamed Bad Likert Judge by Palo Alto Networks Unit … [Read more...] about New AI Jailbreak Method ‘Bad Likert Judge’ Boosts Attack Success Rates by Over 60%
News and How to's