{
  "schema_version": "1.2.0",
  "rubric_version": "1.1",
  "license": "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)",
  "record": {
    "id": "O-0213",
    "slug": "zkonduit",
    "title": "Zkonduit",
    "aliases": [],
    "status": "published",
    "last_reviewed": "2026-09-25",
    "review_interval_days": 90,
    "steward": null,
    "provenance": {
      "drafted_by": "ai",
      "reviewed_by": [
        "codex-review"
      ]
    },
    "risk_flags": [],
    "flags": [],
    "kind": "company",
    "homepage": "https://ezkl.xyz/",
    "one_liner": "The company that makes EZKL, a library for proving in zero knowledge that a neural network produced a given output.",
    "sources": [
      {
        "source": "S-3561",
        "supports": "self-description of EZKL; Zkonduit copyright",
        "locator": "documentation home"
      },
      {
        "source": "S-1806",
        "supports": "EZKL: ONNX models compiled to halo2 circuits; public or private model and data; Zkonduit Inc. as maintainer",
        "locator": "README"
      },
      {
        "source": "S-0024",
        "supports": "two EZKL authors; verifiable evaluations with EZKL; model sizes up to about a million parameters",
        "locator": "author list; §6.1 Table 1"
      },
      {
        "source": "S-0070",
        "supports": "Trail of Bits audit and limited fix review: 34 findings, 8 high resolved, 3 other findings partially resolved, 2 unresolved"
      }
    ],
    "type": "organization",
    "url": "https://trustbutveri.fyi/organizations/zkonduit/",
    "source_file": "content/organizations/zkonduit.md",
    "flags_all": [],
    "body_markdown": "Zkonduit Inc. develops EZKL, which its documentation describes as \"a developer-friendly system for verifiable AI and analytics\" [[S-3561]]. Its verification work is [[I-0014]]:\n\n- EZKL compiles a model exported in the ONNX format into a halo2 circuit, so a prover can show that a model produced an output while keeping either the model or the data private [[S-1806]]. See [[M-0004|zero-knowledge proofs of inference]].\n- Two of the authors of South et al. are from EZKL. The paper uses EZKL to attest that a model with private weights reaches a stated score, with proofs for models of up to about a million parameters [[S-0024]].\n- Trail of Bits reviewed EZKL for Zkonduit in January 2025 and reported 34 findings, 8 of high severity. Its March fix review marked all eight high-severity findings resolved, three other findings partially resolved and two unresolved [[S-0070]].",
    "body_text": "Zkonduit Inc. develops EZKL, which its documentation describes as \"a developer-friendly system for verifiable AI and analytics\" [S-3561]. Its verification work is EZKL: - EZKL compiles a model exported in the ONNX format into a halo2 circuit, so a prover can show that a model produced an output while keeping either the model or the data private [S-1806]. See zero-knowledge proofs of inference. - Two of the authors of South et al. are from EZKL. The paper uses EZKL to attest that a model with private weights reaches a stated score, with proofs for models of up to about a million parameters [S-0024]. - Trail of Bits reviewed EZKL for Zkonduit in January 2025 and reported 34 findings, 8 of high severity. Its March fix review marked all eight high-severity findings resolved, three other findings partially resolved and two unresolved [S-0070].",
    "referenced_by": [
      {
        "id": "I-0014",
        "title": "EZKL",
        "url": "https://trustbutveri.fyi/implementations/ezkl/"
      },
      {
        "id": "S-3561",
        "title": "EZKL documentation (overview)",
        "url": "https://trustbutveri.fyi/sources/ezkl-docs-overview/"
      },
      {
        "id": "S-0024",
        "title": "Verifiable evaluations of machine learning models using zkSNARKs",
        "url": "https://trustbutveri.fyi/sources/south-verifiable-evaluations-zksnarks/"
      },
      {
        "id": "S-1806",
        "title": "zkonduit/ezkl (GitHub repository)",
        "url": "https://trustbutveri.fyi/sources/zkonduit-ezkl-code/"
      }
    ]
  }
}