AI RESEARCH
Bit-Exact AI Inference Verification Without Performance Tradeoffs
arXiv CS.LG
•
ArXi:2606.00279v1 Announce Type: cross Verifying claims about AI workloads is a pre- requisite for credible AI governance of covert adversaries (who comply with monitoring only when detection likelihood is high), yet the ap- parent non-determinism of GPU floating-point arithmetic forces auditors to accept approximate output matches. Covert adversaries can exploit un- verifiable degrees of freedom in monitored compu- tation. Attack vectors include steganography, un- reported modification of inference software, and covert computation via unreported batch elements.