Attestable

A company developing zero-knowledge proofs for AI systems; it reports a prover for large language model inference and proposes proof-based compute accounting.

attestable.com

Attestable says it develops zero-knowledge proofs for AI systems 1. It has published the following on verification:

  • Attestable reports a zero-knowledge prover for production-scale transformer inference whose security rests only on cryptographic hash functions 2. See Attestable zero-knowledge inference prover and zero-knowledge proofs of inference.
  • It proposes combining inference proofs with proof-of-work accounting, and notes that the verifier "needs a credible estimate of the compute available" to the actor 3; see Proofs of useful work for capacity accounting.
  • It proposes a verification firewall at the external interfaces of an environment that holds model weights, which would select outputs for proof at random after each output is committed 4.
On this page

Implementations

Implementations this organization develops.

Mechanisms and implementations whose records cite or describe this organization's work.

Publications

Sources this organization authored or published.

Sources

  1. BAttestable homepage. Attestable. Source recordSupports: development of zero-knowledge proofs for AI systems
  2. CAttestable (2026). Proving LLMs at Scale. Attestable blog. Source recordSupports: zero-knowledge prover for production-scale transformer inference; hash-only security (provider-reported)
  3. CAttestable (2026). Pacing AI Requires Proof. Attestable blog. Source recordSupports: proposal to combine inference proofs with proof-of-work accounting; need for a compute estimate
  4. CAttestable (2026). From Verifiability to Model-Weight Security. Attestable blog. Source recordSupports: verification-firewall proposal with randomly selected proofs

Search

Full search page