Join our Newsletter — 33% off our NHI Course

Why do fine-tuned models pass attestation while inputs stay hidden?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 2 years ago
Posts: 20225
Topic starter  

TL;DR: Fine-tuned models can still hide unverified upstream inputs, Jozu reports, when build records do not bind base model and dataset digests. Provenance controls have to connect attestation to the full model graph before release.

Editorial analysis by NHI Mgmt Group, based on content published by Jozu: “Signing Is Not Enough: Why AI Artifact Provenance Needs to Be a Graph”.

Key questions

Q: Why do signed AI artifacts still leave a governance gap?

A: Because a signature proves integrity of the final artifact, not that the artifact was assembled from approved or policy-compliant inputs.

Q: How should teams validate third-party model provenance before deployment?

A: They should validate provenance as part of a formal intake process that includes source review, conversion review, and trigger testing.

Q: How should teams prove what a fine-tuned model was built from?

A: Teams should prove composition by recording every consumed input by digest at build time and attaching a signed provenance attestation to the output.

Practitioner guidance

  • Record consumed inputs by digest Capture the base model and dataset digests before fine-tuning starts, and write them into the build provenance so downstream verification can match what was actually used.
  • Bind provenance to the build identity Ensure the pipeline identity that runs fine-tuning is the same identity that signs the resulting attestation, so the provenance record is attributable and auditable.
  • Verify the upstream attestation chain recursively Check the final model, then resolve each resolved dependency and confirm its required import or scan attestations before promotion to production.

Bottom line: A fine-tuned model can be legitimately signed and still hide unverified upstream inputs if the build record does not bind the inputs by digest.

Glossary terms: Provenance Attestation, Resolved Dependency, Provenance Graph, Model Lineage

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →


This topic was modified 1 week ago by NHI Mgmt Group

   
Quote
(@mr-nhi)
Member Moderator
Joined: 6 months ago
Posts: 20715
 

Artifact signatures are not provenance proofs. The article correctly separates integrity from composition, and that distinction matters across AI supply chains as much as it does in software delivery. A signed model can still hide unverified upstream data, inherited bias or policy failures if the build record does not bind inputs by digest. Practitioners should treat the final signature as one control layer, not the whole assurance story.

A few things that frame the scale:

  • 7% of security leaders admit they do not know how often their AI systems are making autonomous changes to infrastructure, according to the 2026 Infrastructure Identity Survey.

A question worth separating out:

Q: What is the difference between an SBOM and a provenance attestation?

A: An SBOM describes what should be in the model lineage, while a provenance attestation is a cryptographic statement about what the build process actually consumed. The SBOM gives visibility into relationships such as training inputs; the attestation gives proof that those relationships were real at build time.

👉 Read our full editorial: Fine-tuned model provenance needs graph verification, not just signing


This post was modified 1 week ago by NHI Mgmt Group

   
ReplyQuote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.