新的 Android GUI Agent 漏洞利用了多模态模型的弱点

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-16 04:00

研究人员发现了一种针对由大型多模态模型驱动的 Android GUI Agent 的新型安全漏洞。这些 Agent 旨在感知屏幕内容并注入输入，但容易受到“动作重绑定”（Action Rebinding）攻击。恶意应用程序可以利用这些 Agent 中固有的观察-动作差距，劫持其执行并执行特权操作，而无需危险的权限。该攻击在劫持原子操作和编排未经授权的文件删除和短信发送等高影响利用方面取得了 100% 的成功率，同时逃避了商业恶意软件扫描程序的检测。 AI

影响突出了多模态 Agent 关键的安全盲点，可能影响 AI Agent 在移动平台上的安全部署。

排序理由学术论文，详细介绍了新型安全漏洞。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了新型安全漏洞。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, paper; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 84 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yi Qian, Kunwei Qian, Xingbang He, Ligeng Chen, Jikang Zhang, Tiantai Zhang, Haiyang Wei, Linzhang Wang, Hao Wu, Bing Mao · 2026-07-16 04:00

Mind the Gap：针对Android GUI代理的动作重绑定攻击

arXiv:2601.12349v3 Announce Type: replace-cross Abstract: Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content and inject inputs across application boundaries. While these agents aim to automa…

本文如何被排名

报道来源 [1]

Mind the Gap：针对Android GUI代理的动作重绑定攻击

相关实体

相关话题