Signals 4 · free daily AI digest

ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions

Paper recorded by Signals 4 on 2026-09-16 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-16 on arXiv · recorded by Signals 4 on 2026-09-17

Category: cs.AI · 人工智能 · first seen 2026-09-17

Abstract

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, a

Read on arXiv →

#38 most recent of 300 cs.AI papers we have recorded · ↑ newer: Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Ben · ↓ older: Decodable but Misrouted: Sparse Features Uncover a Readout Gap in Visi
Cite this page: ASLEval: Measuring Privacy Exposure Displacement in LLM Agent Sessions: the #38 most recent of 300 cs.AI papers we have recorded (as of 2026-09-16). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/asleval-measuring-privacy-exposure-displacement-in-llm-agent-sessions.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions