Skip to content

hstre/MIVP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Model Identity Verification Protocol (MIVP)

A cryptographic attestation standard for deployed AI systems.

Version 2.1 · February 2026
Technical Specification · SSRN Working Paper [link to be added]


The Problem

When you interact with an AI system, you cannot independently verify:

  • Which model weights are actually responding
  • Which system policy is active
  • Whether routing or silent model substitution occurred during your session
  • Whether configuration changed between requests

Operators can claim to run any model. There is currently no cryptographic mechanism to verify this claim. MIVP solves this.


What MIVP Does

MIVP defines a deterministic, multi-layer identity model based on cryptographic hashing and Merkle tree commitments. Four hash layers combine into a single Composite Instance Hash (CIH) that uniquely identifies a deployed model instance:

Layer Component What it covers
MH Model Hash Weights, tokenizer, architecture — Merkle root over chunked artifacts
PH Policy Hash System prompt, guardrail rules, moderation layer
RH Runtime Hash Temperature, top-p, max tokens, tooling, routing flags
CIH Composite Instance Hash **SHA256(MH

Any change to weights, policy, or runtime changes the CIH. The CIH can be cryptographically signed by the operator and verified by any client.


What MIVP Enables

  • Silent substitution detection — compare CIH across requests; any change signals routing or model switch
  • Policy change detection — PH changes when system prompt or guardrails change
  • Reproducibility — same CIH guarantees identical deployment configuration
  • Audit and compliance — cryptographically verifiable identity for regulated deployments
  • No trusted hardware required — format-agnostic, compatible with existing deployment pipelines

MIVP does not verify correctness, alignment, or safety. It verifies identity only. Identity is the prerequisite for all higher-level guarantees.


Design Principles

MIVP follows the pattern of established internet trust infrastructure:

  • HTTPS replaced HTTP for transport identity
  • Code signing replaced unsigned executables
  • Secure Boot replaced unsigned firmware

In each case, systems capable of producing verifiable identity proofs gained structural advantages. MIVP applies this pattern to AI model identity.


Specification Contents

The full specification (MIVP_2_1_Complete_Specification.pdf) includes:

  • Core protocol — four hash layers, CIH construction, attestation format, verification procedure
  • Appendix A — Merkle specification for model weights (chunking, tree construction, carry-up logic, test vectors)
  • Appendix B — Policy canonicalization (field-level normalization, JSON serialization rules)
  • Appendix C — Composite Instance Hash specification
  • Appendix D — Runtime Hash specification
  • Appendix E — Instance Attestation format
  • Appendix F — Session Continuity Protocol (ASK/ORK model)
  • Appendix G — Normative test vectors (implementations MUST produce byte-identical CIH values)
  • Appendix H — Structural adoption dynamics
  • Appendix I — Implementation guidance for deterministic compliance (critical failure modes for LLM-generated code)

Implementation Status

No reference implementation exists yet.

The specification is complete and includes normative test vectors (Appendix G) and explicit implementation constraints (Appendix I) designed to prevent the most common failure modes in LLM-assisted code generation.

If you implement MIVP, the test vectors in Appendix G are your compliance baseline: byte-identical CIH output is required for interoperability.


Relation to Alexandria Protocol

MIVP and the Alexandria Protocol address complementary verification problems:

  • MIVP verifies which system produced a knowledge claim — model identity, policy, configuration
  • Alexandria verifies the epistemic structure of the claim itself — derivation path, assumptions, revision history

Together they provide end-to-end verifiability: from the identity of the system that generated a claim, to the structural integrity of the claim itself.


Contact

H.-Steffen Rentschler
Independent researcher
SSRN author


License

MIT. Implement freely, cite honestly.

About

Cryptographic attestation standard for AI model identity. Verifies which model, policy, and configuration is active — enables silent substitution detection without trusted hardware.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages