aiqbench analysis
This research addresses the critical privacy risks inherent in screenshot-based mobile GUI agents, which inadvertently expose sensitive user data unrelated to specific tasks. The proposed CAPED framework introduces a phone-side layer that selectively masks incidental visual content while preserving necessary UI elements for agent operation. By balancing task utility with reduced leakage during remote execution, this work advances security protocols essential for the deployment of autonomous multimodal systems on consumer devices.
CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents
arXiv:2606.12666v2 Announce Type: replace-cross Abstract: Screenshot-based mobile GUI agents can operate ordinary smartphone apps through the same visual interface as a human user, but this capability also turns every screen observation into a privacy boundary. During normal task execution, screenshots may expose contacts, messages, photos, files, recommendations, health cues, and other sensitive context that is unrelated to the user's request. We call this problem incidental visual privacy exposure. It is difficult to address with existing defenses: text anonymization misses many visual and inferential cues, while generic privacy masking can remove the evidence and controls that a GUI agent needs to complete the task. This paper presents CAPED, a context-aware pre-upload exposure control layer for mobile GUI agents. CAPED is designed as a phone-side protection layer: before screenshots are released to a remote multimodal agent, it extracts task requirements, uses screen context as a privacy prior, parses visible UI elements, and selectively exposes only content needed for the current task while masking incidental private content. We evaluate CAPED on AndroidWorld for broad task utility and with a controlled 28-task seeded privacy evaluation used as a measurement instrument for trajectory-level incidental leakage. In this seeded evaluation, Full CAPED reduces success-conditioned weighted seeded leakage from 0.766 under raw screenshots to 0.268 while preserving high task utility. A broader AndroidWorld run shows a remaining prototype-level utility cost, but the results show that task-driven selective exposure can reduce incidental visual leakage before screenshots are released to a remote GUI agent.
Abstract:Screenshot-based mobile GUI agents can operate ordinary smartphone apps through the same visual interface as a human user, but this capability also turns every screen observation into a privacy boundary. During normal task execution, screenshots may expose contacts, messages, photos, files, recommendations, health cues, and other sensitive context that is unrelated to the user's request. We call this problem incidental visual privacy exposure. It is difficult to address with existing defenses: text anonymization misses many visual and inferential cues, while generic privacy masking can remove the evidence and controls that a GUI agent needs to complete the task. This paper presents CAPED, a context-aware pre-upload exposure control layer for mobile GUI agents. CAPED is designed as a phone-side protection layer: before screenshots are released to a remote multimodal agent, it extracts task requirements, uses screen context as a privacy prior, parses visible UI elements, and selectively exposes only content needed for the current task while masking incidental private content. We evaluate CAPED on AndroidWorld for broad task utility and with a controlled 28-task seeded privacy evaluation used as a measurement instrument for trajectory-level incidental leakage. In this seeded evaluation, Full CAPED reduces success-conditioned weighted seeded leakage from 0.766 under raw screenshots to 0.268 while preserving high task utility. A broader AndroidWorld run shows a remaining prototype-level utility cost, but the results show that task-driven selective exposure can reduce incidental visual leakage before screenshots are released to a remote GUI agent.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
arXiv:2606.12666 [cs.CR]
(or arXiv:2606.12666v2 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2606.12666 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 336 words
Related coverage
CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents
arXiv · Jun 12, 2026

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

[AINews] not much happened today
Latent Space · Sep 10, 2026

Article: Artificial Intelligence-Driven Phishing: How Phishing Technique Is Evolving and Implemented
InfoQ · Jun 8, 2026