Skip to content
CASRAI·Indexed by this site · Originally published· Attacks →· Its place in the scan record →

PolicySniff preprint: agent approval policies leak on shared GPUs

PolicySniff Preprint: Shared-GPU Policy Leakage — CASRAI

AI summary

In the PolicySniff preprint submitted to arXiv on November 12, 2026, Weimin Fu and other authors report that shared GPU execution can infer the approval rules an AI agent is using, with a balanced accuracy of 94.17% in the main evaluation on tasks without prior authorization for identifying the current setting, and 88.82% on tasks where the two settings produce the same decision. The experiments were limited to an eager sparse mixture-of-experts runtime using Qwen3-30B-A3B-Instruct-2507, the coverage study was conducted on a single A100 GPU, the observer shared a MIG instance with the agent, and the observer knew the candidate rules and the specific task; observation also caused a noticeable slowdown. The article distinguishes the problem into three independent evaluation questions—behavioral compliance, configuration confidentiality, and authorization enforcement—and emphasizes that these are the authors' experimental results, do not constitute a general attack against deployed agents, and did not achieve arbitrary prompt recovery or unauthorized operations; arXiv moderation is not peer review.

Related papers
Read originalcasrai.org