SOURCE-LINKED INTELLIGENCE

ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Privacy evaluations of tool-using LLM agents often inspect a designated action, final response, or attacker report. These local proxies can miss unauthorized exposure elsewhere in a multi-step session and lack common ground truth across outlets, reports, and tool paths. We introduce privacy exposure displacement, the mismatch between a local evaluation proxy and target-grounded session exposure, and ASLEval, an authorization-aware framework that pre-registers a hidden target set, measures all declared visible exits, and reserves internal traces for diagnosis. Across multiple enterprise-style e

Read original source ↗ Open in workspace

recordType

paper

region

Global