New LLM Jailbreak Uses Models' Evaluation Skills Against Them

SC Media reports on a new jailbreak method for large language models (LLMs) that "takes advantage of models' ability to identify and score harmful content in order to trick the models into generating content related to malware, illegal activity, harassment and more.
"The 'Bad Likert Judge' multi-step jailbreak technique was developed and tested by Palo Alto Networks Unit 42, and was found to increase the success rate of jailbreak attempts by more than 60% when compared with direct single-turn at