arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.04009cs.CR
收藏

ASPIRER:利用大语言模型中基于排列的后门绕过系统提示词

ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs

Lu Yan, Siyuan Cheng, Xuan Chen, Kaiyuan Zhang, Guangyu Shen, Zhuo Zhang, Xiangyu Zhang

AI总结:

本文提出名为ASPIRER的基于排列触发器的LLM后门攻击,可绕过系统提示词防护,在5个主流模型上实现最高99.50%的攻击成功率,揭示了LLM部署供应链的安全漏洞。

摘要:

大语言模型(LLM)已成为众多应用的核心组成部分,系统提示词则是规范模型行为、确保输出符合伦理的关键机制。本文提出一种新型后门攻击,可系统性绕过这些系统提示词,给AI供应链带来重大风险。在正常情况下,模型会严格遵守其系统提示词,但我们的后门可让恶意行为者在触发时绕开这些安全防护。具体而言,我们研究了这样一种场景:LLM提供商在基础模型中嵌入隐蔽触发器,下游部署方对隐藏触发器毫不知情,对模型进行微调后将其作为服务提供给用户,恶意行为者可从提供商处购买触发器,利用它攻击已部署的模型,禁用系统提示词并获取受限结果。我们的攻击采用排列触发器,仅当其组成部分按精确顺序排列时才会激活,这使得检测或逆向工程该触发器的计算难度极高。我们在5个最先进的模型上评估了该方法,结果表明,即使经过防御性微调,本方法的攻击成功率(ASR)仍高达99.50%,同时保持98.58%的干净准确率(CACC)。这些发现揭示了LLM部署流程中的关键漏洞,也凸显了构建更强防御机制的必要性。

英文摘要:

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that systematically bypasses these system prompts, posing significant risks to the AI supply chain. Under normal conditions, the model adheres strictly to its system prompts. However, our backdoor allows malicious actors to circumvent these safeguards when triggered. Specifically, we explore a scenario where an LLM provider embeds a covert trigger within the base model. A downstream deployer, unaware of the hidden trigger, fine-tunes the model and offers it as a service to users. Malicious actors can purchase the trigger from the provider and use it to exploit the deployed model, disabling system prompts and achieving restricted outcomes. Our attack utilizes a permutation trigger, which activates only when its components are arranged in a precise order, making it computationally challenging to detect or reverse-engineer. We evaluate our approach on five state-of-the-art models, demonstrating that our method achieves an attack success rate (ASR) of up to 99.50% while maintaining a clean accuracy (CACC) of 98.58%, even after defensive fine-tuning. These findings highlight critical vulnerabilities in LLM deployment pipelines and underscore the need for stronger defenses.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑