method · first seen 30 Oct 2026
zero-knowledge proofs of machine learning inference
Also: zkML, verifiable inference, zero-knowledge machine learning, zero-knowledge proof of inference
Cryptographic proofs that a model inference was computed correctly without revealing the model or inputs.
Zero-knowledge proofs of ML inference (zkML) let a prover show that a specific committed model produced a given output, without revealing the weights or inputs. The newer direction in these sources is scaling this to transformer LLMs with bit-exact semantics. One paper presents Sable, a small-field sumcheck argument with a single-GPU prover for integer-quantized transformers. Another builds a fully integer-arithmetic runtime so that inference is reproducible and therefore checkable. A third argues that generic inference proofs miss request and checkpoint binding for reward-model services. Others include a hardware-cost breakdown of proving, an unmaintained Lean research prototype under the anthropics account, and a Mac chat app advertising verifiable inference.
If proving costs keep falling, API users and alignment or audit pipelines could check that a provider actually ran the claimed model rather than relying on trust. The emphasis on deterministic integer inference may also matter for reproducibility on its own, separate from cryptography.
Analyst note (emerging), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 2 on 16 Nov 2026 · 6 mentions in 28 days · 6 independent groups · code → papers · first seen 2 weeks ago · acceleration +0.41
Earliest sources
- anthropics/FlashProveCode · 30 Oct 2026 · anthropics · 1,067 stars
- tokenfunplus/coveCode · 6 Nov 2026 · tokenfunplus · 42 stars
- Deterministic, Reproducible Inference in Exact Integer Arithmetic, and Verifiable Distributed Inference as Its ConsequencePapers · 10 Nov 2026 · Sayed Amir Karim
- Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language ModelsPapers · 10 Nov 2026 · Tomer Solberg
- VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM AlignmentPapers · 11 Nov 2026 · Guofu Liao, Hailang Xi, Taotao Wang, Shengli Zhang, Rongcheng Tu, Hao Liao
- Infrastructure for Verifiable AI: Where Proof Costs Go and How Hardware Can HelpPapers · 12 Nov 2026 · Yihan Xia, Wenxin Xu, Taotao Wang
Latest sources
- Infrastructure for Verifiable AI: Where Proof Costs Go and How Hardware Can HelpPapers · 12 Nov 2026 · Yihan Xia, Wenxin Xu, Taotao Wang
- VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM AlignmentPapers · 11 Nov 2026 · Guofu Liao, Hailang Xi, Taotao Wang, Shengli Zhang, Rongcheng Tu, Hao Liao
- Sable: A Small-Field Sumcheck Argument for Bit-Exact Inference of Large Language ModelsPapers · 10 Nov 2026 · Tomer Solberg
- Deterministic, Reproducible Inference in Exact Integer Arithmetic, and Verifiable Distributed Inference as Its ConsequencePapers · 10 Nov 2026 · Sayed Amir Karim
- tokenfunplus/coveCode · 6 Nov 2026 · tokenfunplus · 42 stars
- anthropics/FlashProveCode · 30 Oct 2026 · anthropics · 1,067 stars
Mentioned together with
In the ledger
- 2026-W47 · call #2 · open