English(EN) Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible

新框架为移动GUI代理匿名化敏感数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-28 04:00

研究人员开发了一种新颖的移动GUI代理隐私保护框架，该框架利用多模态大型语言模型。该系统通过使信息可用但对代理不可见来解决敏感数据泄露的风险。它通过用保留类型的占位符替换个人身份信息（PII）来实现这一点，从而在删除具体细节的同时保留语义类别。实验表明，与现有方法相比，这种方法提供了更优的隐私-效用权衡。 AI

影响增强了处理移动设备上敏感用户数据的AI代理的隐私性。

排序理由这是一篇详细介绍AI代理隐私保护新框架的研究论文。

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: Research; 这是一篇详细介绍AI代理隐私保护新框架的研究论文。
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: 163 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) · Lepeng Zhao, Zhenhua Zou, Shuo Li, Zhuotao Liu · 2026-04-28 04:00

增强匿名化的移动GUI代理隐私保护：可用但不可见

arXiv:2602.10139v3 Announce Type: replace-cross Abstract: Mobile Graphical User Interface (GUI) agents have demonstrated strong capabilities in automating complex smartphone tasks by leveraging multimodal large language models (MLLMs) and system-level control interfaces. However,…

本文如何被排名

报道来源 [1]

增强匿名化的移动GUI代理隐私保护：可用但不可见

相关实体

相关话题