New AI Jailbreak Method ‘Bad Likert Judge’ Boosts Attack Success Rates by Over 60%

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 strateg… Continue reading New AI Jailbreak Method ‘Bad Likert Judge’ Boosts Attack Success Rates by Over 60%

Posted in Uncategorized