Pith. sign in

REVIEW 3 cited by

Trustless Audits without Revealing Data or Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.04500 v1 pith:VJETHKEZ submitted 2024-04-06 cs.CR cs.AIcs.CYcs.LG

classification cs.CRcs.AIcs.CYcs.LG
keywords modeldataauditauditsmodelsprovidersallowalongside
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholder wishing to know whether their copyrighted works have been used during training must convince the model provider to allow a third party to audit the model and data. Finding a mutually agreeable third party is difficult, and the associated costs often make this approach impractical. In this work, we show that it is possible to simultaneously allow model providers to keep their model weights (but not architecture) and data secret while allowing other parties to trustlessly audit model and data properties. We do this by designing a protocol called ZkAudit in which model providers publish cryptographic commitments of datasets and model weights, alongside a zero-knowledge proof (ZKP) certifying that published commitments are derived from training the model. Model providers can then respond to audit requests by privately computing any function F of the dataset (or model) and releasing the output of F alongside another ZKP certifying the correct execution of F. To enable ZkAudit, we develop new methods of computing ZKPs for SGD on modern neural nets for simple recommender systems and image classification models capable of high accuracies on ImageNet. Empirically, we show it is possible to provide trustless audits of DNNs, including copyright, censorship, and counterfactual audits with little to no loss in accuracy.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. White Box Evidence Packages for Policy Audit Reports

    cs.CY 2026-07 conditional novelty 6.0 of 10

    In a 60-case controlled audit study, adding white-box model evidence to an LLM auditor increased citation volume but weakened passage grounding and raised evidence misuse, while a shuffled control showed reports can s...

  2. Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment

    cs.CY 2025-07 conditional novelty 6.0 of 10

    Countries could verify compliance with international AI agreements through six redundant verification layers, provided the report's listed hardware and analysis challenges are solved.

  3. ZKTorch: Compiling ML Inference to Zero-Knowledge Proofs via Parallel Proof Accumulation

    cs.CR 2025-07 conditional novelty 6.0 of 10

    ZKTorch compiles machine learning models into basic cryptographic blocks and uses a parallelized accumulation scheme to generate compact zero-knowledge proofs of inference for all MLPerf edge models.

Pith tools