Deutsch(DE) Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents

新框架AgentGhost揭示MLLM GUI代理中的后门风险

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-16 04:00

研究人员开发了一个名为AgentGhost的新框架，用于识别多模态大语言模型（MLLM）驱动的移动GUI代理中的后门漏洞。这些代理由于高昂的微调成本而常被使用，容易受到供应链攻击。AgentGhost结合了目标和交互级别的触发器来激活后门，同时保持任务效用，在移动基准测试中实现了99.7%的攻击准确率，而效用仅下降1%。提出的防御方法将攻击准确率降低到22.1%。 AI

影响强调了MLLM驱动的代理中潜在的安全风险，需要强大的防御措施来维护供应链的完整性。

排序理由该集群包含一篇学术论文，详细介绍了一种识别AI系统漏洞的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 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; 该集群包含一篇学术论文，详细介绍了一种识别AI系统漏洞的新方法。[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: paper, safety; 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: 91 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.CL TIER_1 Deutsch(DE) · Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Zhuosheng Zhang, Gongshen Liu · 2026-06-16 04:00

隐藏的鬼手：揭秘MLLM驱动的移动GUI代理中的后门漏洞

arXiv:2505.14418v3 Announce Type: replace Abstract: Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or…

本文如何被排名

报道来源 [1]

隐藏的鬼手：揭秘MLLM驱动的移动GUI代理中的后门漏洞

相关实体

相关话题