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	Only the title, authors and abstract were read, on the ICML 2026 workshop virtual page (https://icml.cc/virtual/2026/78565), most recently on 2026-10-20. The OpenReview paper remained inaccessible in that check.
Accessed	2026-10-20
Imported from	hodgkins-ai-verification-papers@c71e59ff0e8e
Note	Listed under "Inference verification" in the Hodgkins bibliography (CC BY 4.0).

Cited by