Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak

arXiv:2312.04127v2 Announce Type: replace
Abstract: Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak Attack". In our research, we introduce a novel automatic jailbreak method RADIAL, which bypasses the security mechanism by amplifying the potential of LLMs to generate affirmation responses. The jailbreak idea of our method is "Inherent Response Tendency Analysis" which identifies real-world …

abstract arxiv cs.cl generate jailbreak language language models large language large language models llms novel research responses safety type work world