arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.16965cs.CRcs.AI
收藏

WIPI:针对LLM驱动Web智能体的一种新型Web威胁

WIPI: A New Web Threat for LLM-Driven Web Agents

NVIDIA(英伟达);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Fangzhou Wu, Shutong Wu, Yulong Cao, Chaowei Xiao

AI总结:

本文提出WIPI威胁,通过网页中间接指令在黑盒环境下控制LLM驱动的Web Agent执行恶意操作,实验显示攻击成功率超90%且具备强鲁棒性。

摘要:

随着大语言模型(LLMs)的快速发展,LLM驱动的Web智能体(简称Web Agents)因其卓越能力而受到广泛关注,其中LLMs作为决策的核心部分,如同人类大脑,配备多种Web工具,能够主动与外部部署的网站进行交互。随着大量Web Agents被发布,且此类LLM系统正在快速发展并日益接近在日常生活中的广泛部署,一个至关重要且紧迫的问题随之而来:“这些Web Agents是否安全?”。在本文中,我们提出了一种新型威胁WIPI,它能够间接控制Web Agent执行嵌入在可公开访问网页中的恶意指令。成功发起WIPI攻击的工作环境为黑盒环境。该方法聚焦于外部网页中间接指令的形式与内容,从而提升攻击的效率和隐蔽性。为评估所提方法的有效性,我们使用7个基于插件的ChatGPT Web Agents、8个Web GPTs以及3个不同的开源Web Agents进行了广泛实验。结果表明,即使在纯黑盒场景下,我们的方法平均攻击成功率(ASR)也超过90%。此外,通过针对不同用户前缀指令的消融研究,我们证明了WIPI具有很强的鲁棒性,能够在多样化的前缀指令下保持高性能。

英文摘要:

With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human brain equipped with multiple web tools to actively interact with external deployed websites. As uncountable Web Agents have been released and such LLM systems are experiencing rapid development and drawing closer to widespread deployment in our daily lives, an essential and pressing question arises: "Are these Web Agents secure?". In this paper, we introduce a novel threat, WIPI, that indirectly controls Web Agent to execute malicious instructions embedded in publicly accessible webpages. To launch a successful WIPI works in a black-box environment. This methodology focuses on the form and content of indirect instructions within external webpages, enhancing the efficiency and stealthiness of the attack. To evaluate the effectiveness of the proposed methodology, we conducted extensive experiments using 7 plugin-based ChatGPT Web Agents, 8 Web GPTs, and 3 different open-source Web Agents. The results reveal that our methodology achieves an average attack success rate (ASR) exceeding 90% even in pure black-box scenarios. Moreover, through an ablation study examining various user prefix instructions, we demonstrated that the WIPI exhibits strong robustness, maintaining high performance across diverse prefix instructions.

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。

↑