cs.AI updates on arXiv.org 07月08日 13:53
Hijacking JARVIS: Benchmarking Mobile GUI Agents against Unprivileged Third Parties
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文首次系统研究了移动GUI代理的脆弱性,引入了攻击模拟框架AgentHazard,并开发了包含3000多个攻击场景的基准测试套件,评估了7种常用GUI代理和5种常见骨干模型,揭示了其易受误导内容影响的问题。

arXiv:2507.04227v1 Announce Type: cross Abstract: Mobile GUI agents are designed to autonomously execute diverse device-control tasks by interpreting and interacting with mobile screens. Despite notable advancements, their resilience in real-world scenarios where screen content may be partially manipulated by untrustworthy third parties remains largely unexplored. Owing to their black-box and autonomous nature, these agents are vulnerable to manipulations that could compromise user devices. In this work, we present the first systematic investigation into the vulnerabilities of mobile GUI agents. We introduce a scalable attack simulation framework AgentHazard, which enables flexible and targeted modifications of screen content within existing applications. Leveraging this framework, we develop a comprehensive benchmark suite comprising both a dynamic task execution environment and a static dataset of vision-language-action tuples, totaling over 3,000 attack scenarios. The dynamic environment encompasses 58 reproducible tasks in an emulator with various types of hazardous UI content, while the static dataset is constructed from 210 screenshots collected from 14 popular commercial apps. Importantly, our content modifications are designed to be feasible for unprivileged third parties. We evaluate 7 widely-used mobile GUI agents and 5 common backbone models using our benchmark. Our findings reveal that all examined agents are significantly influenced by misleading third-party content (with an average misleading rate of 28.8% in human-crafted attack scenarios) and that their vulnerabilities are closely linked to the employed perception modalities and backbone LLMs. Furthermore, we assess training-based mitigation strategies, highlighting both the challenges and opportunities for enhancing the robustness of mobile GUI agents. Our code and data will be released at https://agenthazard.github.io.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

移动GUI代理 安全性研究 攻击模拟框架 基准测试 脆弱性评估
相关文章