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
This article has been indexed from The Hacker News