Metraipolis › archive › dc_75c411ad8a4e

TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models — arXiv:2609.29264

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29264
License (as archived): CC0-1.0
Archived: 2026-10-08T04:27:24.081Z
SHA-256 of the archived text: e49f50974d817c695e98af391a36c7ec44b27249a792ea09ef781699f49a2414
Stable URL of this page: https://metraipolis.com/documento/dc_75c411ad8a4e

How to cite

TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models — arXiv:2609.29264 — arXiv (en), https://arxiv.org/abs/2609.29264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_75c411ad8a4e (Metraipolis archive dc_75c411ad8a4e, sha256 e49f50974d817c695e98af391a36c7ec44b27249a792ea09ef781699f49a2414)

BibTeX

@misc{dc75c411ad8a4e,
  title = {TP-CRIV: A Framework for Third-Party Challenge-Response Identity Verification of AI Models — arXiv:2609.29264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_75c411ad8a4e; sha256 e49f50974d817c695e98af391a36c7ec44b27249a792ea09ef781699f49a2414},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artificial intelligence (AI) models are increasingly deployed through remote services, making model misappropriation a growing concern. Existing approaches, including watermarking, fingerprinting, and model similarity analysis, primarily rely on predefined evidence or direct behavioral comparison and do not explicitly evaluate whether the claimant currently possesses and can utilize model-dependent information relevant to the claimed model identity. In this paper, we propose Third-Party Challenge-Response Identity Verification (TP-CRIV) for AI models. TP-CRIV targets a third-party verification setting in which the verifier has neither white-box nor API access to the claimant's model, can interact with the suspicious deployed service only through its ordinary black-box inference interface, and does not require protocol-specific cooperation from the service provider. Under these constraints, the framework enables the verifier to obtain empirical evidence as to whether the claimant locally possesses a model satisfying a predeclared identity relative to the deployed model. Verification is conducted under fresh, previously undisclosed requirements and network isolation, so that the demonstrated capability cannot rely on online external assistance after challenge disclosure. The resulting evidence is interpreted relative to independently specified and calibrated matching and non-matching operating situations and is statistical rather than cryptographic. We instantiate TP-CRIV for CNN image classifiers using probability-control-based witness generation. Experiments on ten ImageNet-pretrained TorchVision models demonstrate clear same/cross-model separation and finite-challenge verification using independently calibrated thresholds.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.29264 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T03:50:58.033Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).