Metraipolis › archive › dc_debf58119ac7
Privacy-Preserving AI Verification via Minimal Information Disclosure — arXiv:2608.02774
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.02774
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:17:45.168Z
- SHA-256 of the archived text
d0d0edd78e81e2cfcdf48dc10c9a95fa147c43995f82cbeb1c08661854ee035a- Stable URL of this page
https://metraipolis.com/documento/dc_debf58119ac7
How to cite
Privacy-Preserving AI Verification via Minimal Information Disclosure — arXiv:2608.02774 — arXiv (en), https://arxiv.org/abs/2608.02774 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_debf58119ac7 (Metraipolis archive dc_debf58119ac7, sha256 d0d0edd78e81e2cfcdf48dc10c9a95fa147c43995f82cbeb1c08661854ee035a)
BibTeX
@misc{dcdebf58119ac7,
title = {Privacy-Preserving AI Verification via Minimal Information Disclosure — arXiv:2608.02774},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.02774},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_debf58119ac7; sha256 d0d0edd78e81e2cfcdf48dc10c9a95fa147c43995f82cbeb1c08661854ee035a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02774. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI verification crosses a trust boundary: a verifier must learn enough to establish an authorized claim, yet the same evidence can reveal sensitive details about the model, workload, or hardware. We introduce minimal information disclosure (MID), which designs and quantifies the information content of verifier-facing evidence itself. MID measures collateral leakage with conditional mutual information: what the release reveals about the protected property after the authorized result is known. MID is general by design: it can accommodate different verification goals, protected properties, evidence sources, and deployment constraints. To demonstrate MID's practicality, we evaluate it on four physical measurements and six verification tasks spanning execution type, hardware identity, compute scale, and model identity. These experiments use three mechanism-design variables--the evidence channel, collection policy, and release transformation--but MID is not limited to these choices and can accommodate other deployable mechanisms. Across these tasks, MID produces three releases with perfect held-out verification and zero measured collateral leakage, while the remaining tasks yield explicit privacy--utility frontiers. MID also supports ZKP-certified releases: we demonstrate our proposed linear-projection mechanism using a Groth16 zk-SNARK. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.02774 — 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 2026-10-31T12:05:52.948Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).