Megadose AI progress, ranked and analyzed.

ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions

· ArXiv · AI/CL/LG ·
The paper says privacy checks that watch only one output can miss nearly half of the exposure in an agent session.

ASLEval defines “privacy exposure displacement” as the gap between a local proxy and what actually leaves through all visible exits. In the reported enterprise-style tests, checking only the expected outlet missed 46.9% of exposure found by the union of visible exits. Attacker self-reports were unreliable, mixing omissions with high false discovery. The authors argue benchmarks should predefine targets and authorization, declare the full visible boundary, and report privacy alongside task utility. ArXiv · AI/CL/LG's note

score 5

Categories: Research