WIPI: A New Web Threat for LLM-Driven Web Agents
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning a High-quality Robotic Wiping Policy Using Systematic Reward Analysis and Visual-Language Model Based Curriculum
Autonomous robotic wiping is an important task in various industries, ranging from industrial manufacturing to sanitization in healthcare. Deep reinforcement learning (Deep RL) has emerged as a promising algorithm, howev…
Deep Reinforcement LearningLanguage ModelingLanguage ModellingLLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By aug…
Language ModelingLanguage ModellingLarge Language ModelRobotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization
We propose a framework to enable multipurpose assistive mobile robots to autonomously wipe tables to clean spills and crumbs. This problem is challenging, as it requires planning wiping actions while reasoning over uncer…
reinforcement-learningReinforcement Learning (RL)Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations
Human conflict is often attributed to threats against material conditions and symbolic values, yet it remains unclear how they interact and which dominates. Progress is limited by weak causal control, ethical constraints…
Agent Safety Alignment via Reinforcement Learning
The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions,…
Reinforcement Learning