Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitization
Quick Answer
MINIM introduces a privacy-aware local broker that minimizes UI state observations before transmission, significantly reducing sensitive data leakage while maintaining task-critical context.
Quick Take
MINIM introduces a privacy-aware local broker that minimizes UI state observations before transmission, significantly reducing sensitive data leakage while maintaining task-critical context. By employing a dual-score system for UI elements, it effectively prunes irrelevant information, enhancing security for LLM-powered agents in complex environments.
Key Points
- MINIM reduces task-irrelevant sensitive data leakage by optimizing UI observations.
- Employs a dual-score system to assess sensitivity and necessity of UI elements.
- Utilizes a ternary disclosure policy to manage sensitive information effectively.
- Experiments show significant preservation of task-critical context in real-world scenarios.
- Designed to enhance privacy for autonomous agents in digital environments.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 13949v1 Announce Type: new Abstract: Modern LLM-powered autonomous agents increasingly rely on rich user interface (UI) state observations to achieve reliable action grounding in complex digital environments. However, many deployments transmit the full UI state to remote inference servers even when most elements are irrelevant to the current task, which can leak sensitive but unnecessary context such as authentication codes, private notifications, and background application states.
We propose MINIM, a trusted local broker that performs privacy-aware minimization on the client side before any observation leaves the device. Grounded in Contextual Integrity (CI), MINIM learns a dual-score representation for each UI element by predicting an inherent sensitivity score (s) and a task-conditioned necessity score (n). These scores drive a ternary disclosure policy that keeps essential elements, abstracts sensitive attributes when needed, and removes task-irrelevant content.
We optimize a CI-aware objective that penalizes necessity errors more strongly on high-risk content, enabling aggressive pruning while preserving task-critical information. Experiments on real-world UI observations derived from WebArena show that MINIM substantially reduces task-irrelevant sensitive leakage while preserving task-critical semantic context and the interactive affordances required for reliable agent actions.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.
