With regards to AI fashions, one of many hardest inquiries to reply is deceptively easy: the place did this mannequin really come from?
We addressed a part of this drawback with Mannequin Provenance Equipment, an open-source device that fingerprints fashions on the weight stage (the parameters that defines what a mannequin is aware of and the way it behaves) to confirm their origins. However a fingerprinting device wants a transparent customary to measure in opposition to, that defines precisely what qualifies as a derivation relationship between two fashions. Right here, the trade doesn’t but have a constant reply.
Definitions differ throughout licensors, requirements of our bodies, analysis teams, and AI labs. The identical pair of fashions will be labeled as “associated” by one reviewed and “impartial” by one other, with each citing defensible reasoning. That inconsistency creates actual issues for licensing enforcement, vulnerability triage, and regulatory compliance.
We created the Mannequin Provenance Structure as an try to repair that. Comprised of a taxonomy, definition, and boundary specs, it is a normative reference, a structure, that specifies what a mannequin provenance relationship is and isn’t on the stage of weight derivation. This submit covers its construction, its reasoning, and the way it connects to the frameworks that governance applications already use. The Mannequin Provenance Structure builds on forthcoming work from Cisco AI Protection that describes the methodology in full, together with empirical proof for why such an strategy is vital for each provenance and detection pipelines. You may assessment the Structure inside the docs folder of the Mannequin Provenance Equipment.
Why Defining Mannequin Provenance is Vital
Basis fashions don’t arrive within the enterprise as remoted artifacts. They get fine-tuned, distilled, quantized, merged, and repackaged, and every step produces a brand new checkpoint whose relationship to its guardian is poorly documented. When a safety crew must know whether or not a deployed mannequin inherits a identified vulnerability, or when compliance wants to find out whether or not a third-party checkpoint triggers a licensing obligation, the query is at all times the identical: is that this mannequin a spinoff of that one?
With out a shared, rigorous reply, group can face compounding dangers:
- Provide chain assaults are already exploiting this hole
- Regulatory necessities assume provenance readability that doesn’t but exist
- Incident response will depend on traceable lineage
Provenance is About Mannequin Weights
The Mannequin Provenance Structure grounds provenance in a single idea: the verifiable derivation historical past of a mannequin’s skilled weights. Two fashions share provenance if, and provided that, a causal chain of weight derivation connects them, whether or not instantly, not directly via distillation, or mechanically via a non-training transformation like quantization.
Shared structure, shared coaching knowledge, shared tokenizer, and shared benchmark efficiency don’t rely. The exclusion is deliberate. A broader definition that handled any architectural or behavioral similarity as derivation might make licensing enforcement apply to each mannequin in an structure household, would flag convergent designs as real vulnerability hyperlinks, and would flood governance audits with false positives. Weight-level causation produces labels which are secure throughout reviewers, strong to metadata manipulation, and aligned with how derivation really occurs in apply.
How Mannequin Provenance Structure is Structured
The structure solutions three questions: when are two fashions associated? How does that relationship happen? And what seems to be like a relationship, however isn’t? It organizes these solutions as specific enumerations fairly than definitions-by-example, so each pair of fashions encountered in apply maps to a transparent class.
5 situations specify when a provenance hyperlink exists
- Direct descent: coaching initialized from a skilled checkpoint
- Oblique descent: distillation from a trainer mannequin
- Mechanical transformation: quantization, pruning, merging, or format conversion
- Identification: byte-equivalent copy
- Transitivity: any composition of the above
A pair is provenance-linked if at the least one situation holds.
9 mechanisms enumerate the concrete derivation pathways noticed in apply:
- Identification and reformatting
- Effective-tuning
- Continued pretraining
- Vocabulary-modified derivation
- Information distillation
- Structural modification with weight inheritance
- Quantization and compression
- Adapter-based derivation (LoRA, QLoRA, prefix tuning)
- Mannequin merging
Eight exclusions listed under are situations that will seem like provenance-linked, however are provenance-independent. Every exclusion is a sample of obvious similarity, however in the end one which carries no weight-derivation chain:
- Unbiased replica (e.g., Llama-2 vs. Open LLaMA which share the identical structure and tokenizer, however are skilled from scratch)
- Identical-family different-size (e.g., Llama-2-7B vs. Llama-2-13B).
- Identical-family different-corpus coaching (e.g., T5 vs. MT5, which share a reputation root, however have separate from-scratch coaching)
- Unbiased runs underneath a shared seed (i.e., shared seed doesn’t represent shared weights)
- Architectural convergence (completely different groups independently arriving at comparable mannequin designs)
- Dimensional coincidence underneath completely different mechanisms (fashions that occur to share the identical measurement or form with out one being constructed from the opposite)
- Shared vocabulary with out weight switch (a tokenizer is a device, not a weight)
- Shared coaching goal (sharing an goal doesn’t hyperlink weights)
A rigorous provenance customary should identify them explicitly, as a result of complicated any of them with real derivation corrupts downstream licensing selections, vulnerability assessments, and compliance determinations.
Establishing an Proof Commonplace
A taxonomy is just as helpful because the proof customary hooked up to it. The Mannequin Provenance Structure accounts for 3 sources for establishing provenance (and however architectural similarity and naming conventions are explicitly inadequate):
- Official documentation: from the releasing group that explicitly names the guardian mannequin and derivation technique
- Checkpoint verification: via hash matching, layer-by-layer comparability, or reproducible derivation scripts
- Authoritative third-party evaluation: that has been peer-reviewed or broadly cited
Beneath ambiguity, Mannequin Provenance Structure defaults to labeling a pair as provenance-independent. This conservatism is intentional. A false optimistic in provenance carries speedy penalties: a licensing accusation, an IP declare, a supply-chain incident notification. A false unfavorable will get caught by defense-in-depth via guide assessment, licensing audit, and forensic evaluation. Specificity wins when rigor is required.
Alignment with AI Risk Frameworks and Requirements
Mannequin provenance attestation will be thought of a provide chain management, and the Mannequin Provenance Structure serves as a definitional layer that makes mannequin dependency auditable. It specifies what it means for a deployed mannequin to inherit from an upstream supply, which is the precondition for any significant query about inherited vulnerabilities, license obligations, or unattributed redistribution.
“weak mannequin provenance” and noting that “no ensures on the origin of the mannequin.” The MITRE ATLAS framework paperwork provide chain compromise (AML.T0010) as a main preliminary-access method. The Cisco AI Safety and Security Framework classifies third-party mannequin elements underneath OB-009 Provide Chain Compromise, with direct applicability via AITech-9.3 (Dependency/Plugin Compromise). The Cisco AI Safety and Security Framework classifies third-party mannequin elements underneath OB-009 Provide Chain Compromise, with direct applicability via AITech-9.3 Dependency / Plugin Compromise: actors insert malicious code, backdoors, or vulnerabilities into third-party dependencies utilized by fashions, brokers, or AI functions, creating supply-chain assaults that have an effect on all methods utilizing the compromised part. Basis-model checkpoints reused as initialization for downstream fashions are exactly such dependencies.
The structure additionally acknowledges the adversarial dimension via AITech-9.2 Detection Evasion: deliberate concealment of a derivation relationship — metadata rewriting, tokenizer substitution, chained modifications supposed to obscure the guardian. The structure’s dedication to weight-level proof, fairly than metadata-level proof, is a direct response to this adversary mannequin.
Mannequin Provenance Structure attracts from current frameworks that AI provide chain applications already depend on. These frameworks determine necessities or concerns that the structure helps fulfill. A proper provenance definition is a precondition for producing that documentation persistently throughout a company and throughout suppliers.
Desk 1. Frameworks, laws, and requirements that Mannequin Provenance Structure drew upon
A Dwelling Doc
New strategies of constructing fashions are rising sooner than any fastened taxonomy can accommodate. Mannequin merging, combining specialised skilled fashions, has turn out to be a dominant method over the previous few years. Past merging, the ecosystem is seeing Combination-of-Specialists architectures with independently skilled elements, federated coaching throughout organizations, and artificial knowledge pipelines that blur the road between information switch and authentic coaching. The Mannequin Provenance Structure considers these open frontiers and commits to revision because the panorama evolves.
Get Began
The total Mannequin Provenance Structure abstract is offered alongside this submit: https://github.com/cisco-ai-defense/model-provenance-kit/tree/predominant/docs/structure
For groups able to put these definitions into apply, Mannequin Provenance Equipment supplies the tooling. All the pipeline runs on CPU, architectural matches resolve in milliseconds, and extracted options are cached for reuse. Try Mannequin Provenance Equipment Github: https://github.com/cisco-ai-defense/model-provenance-kit
Entry a starter set of base mannequin fingerprints on Hugging Face: https://huggingface.co/datasets/cisco-ai/model-provenance-kit