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 42 researchers Yongzhe Huang, Yang Ji, Wenjun Hu, Jay Chen, Akshata Rao, and
Source: Read More