Verifier
The party that examines evidence supplied by, or collected about, a prover and decides whether the prover's claim holds.
A verifier is the party that examines evidence from or about a prover and decides whether the prover's claim holds 1 2.
Under an international agreement the verifier may be another state, an international institution, a government body or a third party 1 3. In proof systems, soundness protects the verifier: if a statement is false, a verifier that follows the protocol will not be convinced 4. The IETF remote-attestation architecture splits the role in two: a verifier appraises evidence and produces attestation results, and a separate relying party acts on them 2. In Shavit's framework the verifier randomly samples and physically inspects accelerators, and re-runs selected training segments as in proof-of-learning 5. In low-trust settings the verifier is itself a potential adversary: one system design assumes it may try to exfiltrate the prover's secrets, so the prover distrusts the devices the verifier relies on 6.
Related
Used in
- R2Confidential multi-party verification
- R1Memory wiping and proofs of secure erasure
- R1Network taps and certifiers
- R2Proof-of-learning and training-transcript verification⚠
- R2Safeguard attestation
- R2Sampled inference recomputation
- R2Tamper evidence for verifier devices
- R2TEE remote attestation for AI workloads⚠
- R1Timed challenge-response and memory-occupation challenges
- R2Zero-knowledge proofs of inference
- R1Low-trust AI compute verification system overview
- R2zkLLM
Sources
- BB. Harack et al. (2025). Verification for International AI Governance. Oxford Martin AI Governance Initiative. Source recordSupports: Verifier defined as an institution, such as another state or an international institution, that assesses the Prover's compliance · p. 18, fn. 20
- BH. Birkholz et al. (2023). Remote ATtestation procedureS (RATS) Architecture (RFC 9334). Internet Engineering Task Force (RATS Working Group). Source recordSupports: Verifier appraises evidence and produces attestation results; Relying Party acts on them · §4 Terminology
- BM. Baker et al. (2025). Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment. RAND Corporation. Source recordSupports: Verifier may be a government body or a third party · §3.1
- BD. Benarroch et al. (2022). ZKProof Community Reference. ZKProof. Source recordSupports: soundness: if the statement is false, a verifier following the protocol will not be convinced · p. 1
- BY. Shavit (2023). What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring. arXiv. Source recordSupports: Verifier randomly samples and inspects chips and re-runs selected training segments · §3.1–3.2; §5.1
- BN. Cankaya (2026). A System Overview for Near-Term, Low-Trust AI Compute Verification. Machine Intelligence Research Institute. Source recordSupports: a malicious verifier may try to exfiltrate confidential information; its devices are verifier-trusted and prover-distrusted · threat model section