On the subject of 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 downside with Mannequin Provenance Equipment, an open-source device that fingerprints fashions on the weight degree (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 towards, that defines precisely what qualifies as a derivation relationship between two fashions. Right here, the trade doesn’t but have a constant reply.
Definitions fluctuate 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 degree of weight derivation. This put up 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 method is important for each provenance and detection pipelines. You possibly can assessment the Structure throughout the docs folder of the Mannequin Provenance Equipment.
Why Defining Mannequin Provenance is Necessary
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 mother or father is poorly documented. When a safety crew must know whether or not a deployed mannequin inherits a recognized vulnerability, or when compliance wants to find out whether or not a third-party checkpoint triggers a licensing obligation, the query is all the time the identical: is that this mannequin a by-product of that one?
And not using 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 is determined by 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 educated weights. Two fashions share provenance if, and provided that, a causal chain of weight derivation connects them, whether or not straight, not directly by means of distillation, or mechanically by means of a non-training transformation like quantization.
Shared structure, shared coaching information, 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 could 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 might be secure throughout reviewers, sturdy 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 appears to be like like a relationship, however isn’t? It organizes these solutions as specific enumerations quite than definitions-by-example, so each pair of fashions encountered in apply maps to a transparent class.
5 circumstances specify when a provenance hyperlink exists
- Direct descent: coaching initialized from a educated checkpoint
- Oblique descent: distillation from a instructor mannequin
- Mechanical transformation: quantization, pruning, merging, or format conversion
- Id: byte-equivalent copy
- Transitivity: any composition of the above
A pair is provenance-linked if at the very least one situation holds.
9 mechanisms enumerate the concrete derivation pathways noticed in apply:
- Id and reformatting
- High quality-tuning
- Continued pretraining
- Vocabulary-modified derivation
- Data distillation
- Structural modification with weight inheritance
- Quantization and compression
- Adapter-based derivation (LoRA, QLoRA, prefix tuning)
- Mannequin merging
Eight exclusions listed under are circumstances which will seem like provenance-linked, however are provenance-independent. Every exclusion is a sample of obvious similarity, however finally 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 educated from scratch)
- Similar-family different-size (e.g., Llama-2-7B vs. Llama-2-13B).
- Similar-family different-corpus coaching (e.g., T5 vs. MT5, which share a reputation root, however have separate from-scratch coaching)
- Unbiased runs beneath a shared seed (i.e., shared seed doesn’t represent shared weights)
- Architectural convergence (totally different groups independently arriving at comparable mannequin designs)
- Dimensional coincidence beneath totally different mechanisms (fashions that occur to share the identical dimension 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 choices, vulnerability assessments, and compliance determinations.
Establishing an Proof Normal
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 mother or father mannequin and derivation methodology
- Checkpoint verification: by means of hash matching, layer-by-layer comparability, or reproducible derivation scripts
- Authoritative third-party evaluation: that has been peer-reviewed or extensively cited
Below ambiguity, Mannequin Provenance Structure defaults to labeling a pair as provenance-independent. This conservatism is intentional. A false constructive in provenance carries rapid penalties: a licensing accusation, an IP declare, a supply-chain incident notification. A false adverse will get caught by defense-in-depth by means of 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 approach. The Cisco AI Safety and Security Framework classifies third-party mannequin elements beneath OB-009 Provide Chain Compromise, with direct applicability by means of AITech-9.3 (Dependency/Plugin Compromise). The Cisco AI Safety and Security Framework classifies third-party mannequin elements beneath OB-009 Provide Chain Compromise, with direct applicability by means of 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 techniques utilizing the compromised part. Basis-model checkpoints reused as initialization for downstream fashions are exactly such dependencies.
The structure additionally acknowledges the adversarial dimension by means of AITech-9.2 Detection Evasion: deliberate concealment of a derivation relationship — metadata rewriting, tokenizer substitution, chained modifications meant to obscure the mother or father. The structure’s dedication to weight-level proof, quite than metadata-level proof, is a direct response to this adversary mannequin.
Mannequin Provenance Structure attracts from present frameworks that AI provide chain applications already depend on. These frameworks establish necessities or concerns that the structure helps fulfill. A proper provenance definition is a precondition for producing that documentation persistently throughout a corporation and throughout suppliers.
Desk 1. Frameworks, rules, and requirements that Mannequin Provenance Structure drew upon
A Residing Doc
New strategies of constructing fashions are rising sooner than any mounted taxonomy can accommodate. Mannequin merging, combining specialised educated fashions, has turn into a dominant approach over the previous few years. Past merging, the ecosystem is seeing Combination-of-Consultants architectures with independently educated elements, federated coaching throughout organizations, and artificial information 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 out there alongside this put up: https://github.com/cisco-ai-defense/model-provenance-kit/tree/essential/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. Take a look at 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