Bit-Exact AI Inference Verification Without Performance Tradeoffs

Computer Science > Cryptography and Security [Submitted on 29 May 2026] Bit-Exact AI Inference Verification Without Performance Tradeoffs Naci Cankaya 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. Empirically, we analyze how modern inference engines (vLLM, HF transformers) produce deter- ministic but non-invariant outputs, without need- ing to set performance-compromising determin- ism flags, if the right information is available for re-computation and no atomic functions are called in the backend. We demonstrate that such bitwise- precise re-computation does not require access to identical hardware, via a software-only emula- tion of LLM inference across multiple NVIDIA GPU variants. Thus, accumulated rounding errors can be an auditable signature of the software and hardware setup used for inference, instead of a constraint on verifiability. Subjects: Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2606.00279 [cs.CR]   (or arXiv:2606.00279v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.00279 Focus to learn more Submission history From: Naci Cankaya [view email] [v1] Fri, 29 May 2026 19:15:15 UTC (146 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)