Zero knowledge verification for frontier AI training is possible

Computer Science > Artificial Intelligence [Submitted on 3 Jun 2026] Zero knowledge verification for frontier AI training is possible Pierre Peigné, Ky Nguyen, Paul Wang Frontier AI governance frameworks increasingly use cumulative training compute as the primary criterion for designating high-impact models, but enforcement rests on self-reporting because no technical verification primitive for training exists. Any future international agreement on frontier AI faces the same problem at higher stakes: coordinated regulation of technologies with significant externalities has historically rested on technical verification, without which agreements are declaratory. Recent governance analyses judge zero-knowledge proofs a promising candidate but currently impractical at frontier scale [26, 4]. We argue the impracticality is paradigm-bound rather than fundamental, and propose a verification architecture for frontier dense pre-training combining a pre-committed training specification, inter-node network observations, and on-the-fly Merkle commitments of intermediate computation, verified through a zero-knowledge Virtual Machine (zkVM) with native BF16/FP32 precompiles. The proof checks the actual floating-point computation the GPU performed rather than a fixed-point approximation, and preserves model-architecture confidentiality through a private training specification. The protocol produces three proof types: a genesis proof at initialisation, in-training step proofs across the run, and ex-ante attestations enforcing policy-relevant claims as running invariants, turning the training record into a governance-enforceable artefact. We estimate a deployable proof of concept within approximately 36 months at single-digit-percent training-side overhead, against a six-to-ten-year cycle for verification-grade custom silicon. Thirteen open research and engineering problems are catalogued as a research agenda for external contribution Comments: 44 pages, 2 figures Subjects: Artificial Intelligence (cs.AI); Systems and Control (eess.SY) Cite as: arXiv:2606.05433 [cs.AI]   (or arXiv:2606.05433v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.05433 Focus to learn more Submission history From: Pierre Peigné [view email] [v1] Wed, 3 Jun 2026 20:57:28 UTC (380 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.SY eess eess.SY 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?)