ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions
[Kryptografia i bezpieczeństwo] Autorzy: Guosen Wu, Huizhen Huang, Guoxiong Long i 2 więcej
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 environments and independently implemented runtimes, we observe three recurring patterns. An expected-outlet-only view misses 46.9% of exposure recovered by the visible-exit union; attacker self-reports combine omissions with high false discovery; and schema-aligned internal evidence usually precede…
- Kategoria arxiv
- cs.CR
- Kategoria
- Kryptografia i bezpieczeństwo