Intention Analysis Makes LLMs A Good Jailbreak Defender

arXiv:2401.06561v2 Announce Type: replace
Abstract: Aligning large language models (LLMs) with human values, particularly in the face of stealthy and complex jailbreak attacks, presents a formidable challenge. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis ($\mathbb{IA}$). The principle behind this is to trigger LLMs' inherent self-correct and improve ability through a two-stage process: 1) essential intention analysis, and 2) policy-aligned response. Notably, $\mathbb{IA}$ is an inference-only method, thus could enhance the safety of …

analysis arxiv cs.cl good jailbreak llms type