With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse, a risk remains, particularly when models encounter adversarial inputs. This study unveils an attack mechanism that capitalizes on human conversation strategies to extract harmful information from LLMs. We delineate three pivotal strategies: (i) decomposing malicious questions into seemingly innocent sub-questions; (ii) rewriting overtly malicious questions into more covert, benign-sounding ones; (iii) enhancing the harmfulness of responses by prompting models for illustrative examples. Unlike conventional methods that target explicit malicious responses, our approach delves deeper into the nature of the information provided in responses. Through our experiments conducted on GPT-3.5-turbo, GPT-4, and Llama2, our method has demonstrated a marked efficacy compared to conventional attack methods. In summary, this work introduces a novel attack method that outperforms previous approaches, raising an important question: How to discern whether the ultimate intent in a dialogue is malicious?

本研究解决了大型语言模型（LLM）在面对对抗输入时的潜在脆弱性。提出了一种新颖的攻击机制，通过人类对话策略提取有害信息，其中包括将恶意问题分解为看似无害的子问题等策略。实验结果表明，所提方法在有效性上显著优于传统攻击方法，提出了如何识别对话中最终意图是否恶意的重要问题。

Imposter.AI：针对一致性大型语言模型的隐蔽意图对抗攻击