# MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution

arXiv: https://arxiv.org/abs/2605.28646 · HTML: https://mlsanity.com/paper/2605.28646/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 25 of 25)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception](https://mlsanity.com/paper/2401.16158/) (2024)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [OmniParser for Pure Vision Based GUI Agent](https://mlsanity.com/paper/2408.00203/) (2024)
- [Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs](https://mlsanity.com/paper/2404.05719/) (2024)
- [GUI Agents with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2411.04890/) (2024)
- [AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents](https://mlsanity.com/paper/2410.24024/) (2024)
- [SkillClaw: Let Skills Evolve Collectively with Agentic Evolver](https://mlsanity.com/paper/2604.08377/) (2026)
- [Memento-Skills: Let Agents Design Agents](https://mlsanity.com/paper/2603.18743/) (2026)
- [PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles](https://mlsanity.com/paper/2410.17127/) (2024)
- [Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents](https://mlsanity.com/paper/2509.17488/) (2025)
- [PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization](https://mlsanity.com/paper/2505.09921/) (2025)
- [Computer-Use Agents as Judges for Generative User Interface](https://mlsanity.com/paper/2511.15567/) (2025)
- [MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents](https://mlsanity.com/paper/2605.09530/) (2026)
- [Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible](https://mlsanity.com/paper/2602.10139/) (2026)
- [TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution](https://mlsanity.com/paper/2602.09662/) (2026)
- [VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering](https://mlsanity.com/paper/2603.13385/) (2026)
- [Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning](https://mlsanity.com/paper/2601.04666/) (2026)

## Built on by (most cited first, 1 of 1)

- [CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents](https://mlsanity.com/paper/2606.12666/) (2026)

## Abstract (arXiv)

GUI agents rely on screenshots to infer intent and operate across applications, but these screenshots often contain private messages, medical records, payment credentials, and workplace-specific workflows. Privacy decisions in this setting depend on task, recipient, application state, and user role, yet static PII detectors miss these boundaries and cloud-side VLM reasoning can upload the raw screen before deciding what should be protected. We present MaskClaw, an edge-side privacy arbitrator for GUI agents. MaskClaw extracts local visual evidence, retrieves user- and task-specific policy memory, and decides Allow, Mask, or Ask before raw screenshots leave a trusted user- or organization-controlled environment. In five designed skill-evolution scenarios, it turns corrections, cancellations, and edits into reusable privacy skills checked by a sandbox gate. We introduce P-GUI-Evo, a benchmark built from real UI patterns, reconstructed HTML screens, and sanitized labels. Experiments show that pattern matching, cloud reasoning, and routing alone tend to over-confirm, over-mask, or expose raw screenshots under the same protocol. The artifact is available at https://github.com/Theodora-Y/MaskClaw.