Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology

arXiv:2402.15690v1 Announce Type: new
Abstract: Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access restricted information, which is called "jailbreaking." Previous studies have shown the weakness of current LLMs when confronted with such jailbreaking attacks. Nevertheless, comprehension of the intrinsic decision-making mechanism within the LLMs upon receipt of jailbreak prompts is noticeably lacking. Our research provides a psychological explanation of the jailbreak prompts. …

abstract arxiv become cognitive cs.ai cs.cl current information jailbreaking knowledge language language model language models large language large language model large language models llms people protection psychology security studies type understanding via