Consortium forVerified Computing

O-0213

Zkonduit

The company that makes EZKL, a library for proving in zero knowledge that a neural network produced a given output.

Source reviewed 2026-09-25

01 / The mechanism and its boundary

What is being described

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.

Organization website ↗

Connections in the research map

Related research

implementation / R2

EZKL

EZKL is a library from Zkonduit that turns neural networks into zero-knowledge circuits, so a prover can show an output came from a committed model.

Sources and provenance

  1. S-3561 / Tier B

    EZKL documentation (overview) ↗

    Zkonduit Inc. · 2025 · EZKL documentation

    Supports: self-description of EZKL; Zkonduit copyright

    Locator: documentation home

    Version and catalogue details
  2. S-1806 / Tier B

    zkonduit/ezkl (GitHub repository) ↗

    Zkonduit Inc. · 2026 · GitHub

    Supports: EZKL: ONNX models compiled to halo2 circuits; public or private model and data; Zkonduit Inc. as maintainer

    Locator: README

    Version and catalogue details
  3. S-0024 / Tier B

    Verifiable evaluations of machine learning models using zkSNARKs ↗

    T. South, A. Camuto, S. Jain, S. Nguyen, R. Mahari, C. Paquin, J. Morton, A. Pentland · 2024 · arXiv

    Supports: two EZKL authors; verifiable evaluations with EZKL; model sizes up to about a million parameters

    Locator: author list; §6.1 Table 1

    Version and catalogue details
  4. S-0070 / Tier B

    Zkonduit EZKL Security Assessment ↗

    F. Casal, T. Hess, L. Bourtoule, S. Hussain, G. Larregay · 2025 · Trail of Bits (prepared for Zkonduit Inc.)

    Supports: Trail of Bits audit and limited fix review: 34 findings, 8 high resolved, 3 other findings partially resolved, 2 unresolved

    Version and catalogue details
Source review date
2026-09-25
Drafted by (source map)
ai
Review handles (source map)
codex-review