Verifying AI Compute by Bounding Unexplained Information Exfiltration

J. Petrie, Y. Mühlhäuser. 2026. ICML 2026 Workshop on Technical AI Governance Research.

Original	https://openreview.net/forum?id=qtgG5HZSsk
Version	OpenReview returned a browser check on 2026-09-23 and 2026-09-25, so only the title, authors and abstract were read, on the workshop's ICML 2026 virtual page (https://icml.cc/virtual/2026/78565). No arXiv version found as of 2026-09-25.
Accessed	2026-09-25
Imported from	hodgkins-ai-verification-papers@c71e59ff0e8e
Note	Listed under "Inference verification" in the Hodgkins bibliography (CC BY 4.0).

Cited by