Large language models (LLMs) have achieved remarkable performance in various natural language processing tasks, especially in dialogue systems. However, LLM may also pose security and moral threats, especially in multi round conversations where large models are more easily guided by contextual content, resulting in harmful or biased responses. In this paper, we present a novel method to attack LLMs in multi-turn dialogues, called CoA (Chain of Attack). CoA is a semantic-driven contextual multi-turn attack method that adaptively adjusts the attack policy through contextual feedback and semantic relevance during multi-turn of dialogue with a large model, resulting in the model producing unreasonable or harmful content. We evaluate CoA on different LLMs and datasets, and show that it can effectively expose the vulnerabilities of LLMs, and outperform existing attack methods. Our work provides a new perspective and tool for attacking and defending LLMs, and contributes to the security and ethical assessment of dialogue systems.

我们提出了一种新的利用上下文反馈和语义相关性的方法，通过与大型模型进行多轮对话来自适应地调整攻击策略，从而使模型产生不合理或有害内容。我们评估了该方法在不同的大型语言模型和数据集上，并展示它可以有效揭示大型语言模型的漏洞，并超越现有的攻击方法。我们的工作为攻击和防御大型语言模型提供了一种新的视角和工具，并为对话系统的安全和伦理评估做出了贡献。

攻击链: 基于语义驱动的上下文式多轮攻击器对LLM的攻击