SOURCE-LINKED INTELLIGENCE

MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific security policies. Existing trajectory-level defenses rely on LLM prompting or rigid rules, and thus fail to support fine-grained, natural-language policies that generalize across apps and tasks. In this work, we introduce MATE, a lightweight, policy-conditioned auditor that encodes both agent trajectories and natural-language security policies to determine whether a trajectory violates a given policy and to explain why. Treating policies as edi

Read original source ↗ Open in workspace

recordType

paper

region

Global