Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations

Large Language Models (LLMs) have shown remarkable success in various tasks, but concerns about their safety and the potential for generating harmful content have emerged. In this paper, we delve into the potential of In-Context Learning (ICL) to modulate the alignment of LLMs. Specifically, we propose the In-Context Attack (ICA), which employs strategically crafted harmful demonstrations to subvert LLMs, and the In-Context Defense (ICD), which bolsters model resilience through examples that demonstrate refusal to produce harmful responses. Through extensive experiments, we demonstrate the efficacy of ICA and ICD in respectively elevating and mitigating the success rates of jailbreaking prompts. Moreover, we offer theoretical insights into the mechanism by which a limited set of in-context demonstrations can pivotally influence the safety alignment of LLMs. Our findings illuminate the profound influence of ICL on LLM behavior, opening new avenues for improving the safety and alignment of LLMs.