Skip to content
Preprint

Privacy-Preserving AI Verification via Minimal Information Disclosure

Aug 2026 · 0 citations · 57 references
Computer Science

TL;DR

This work introduces minimal information disclosure (MID), which designs and quantifies the information content of verifier-facing evidence itself and measures collateral leakage with conditional mutual information.

Abstract

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.

View source

Similar papers

Preprint Aug 2026

The Anonymity Gap: Understanding Real Privacy in Shielded UTXO-based Protocols for DeFi

A layered system model and an analysis pipeline that uses prior history as the temporal baseline, applies cumulative pruning and cross-proof propagation to each proof's Commitment Set, and recursively traces the survivors through historical hidden-state transitions to derive the final transaction-level Anonymity Set Size is proposed.

Hanze Guo, Stefanos Chaliasos, Yebo Feng et al. · 0 citations
Preprint Jul 2026

xChk: Bring Your Own Identity -- Heterogeneous Assurance with Verifier-Determined Sufficiency

We present xChk, a reference identity provider for Bring Your Own Identity (BYOI): users enroll via heterogeneous proofs (government KYC, corporate SSO, WebAuthn/FIDO2, professional networks, live verification, longitudinal activity, behavioral signals) and disclose them as portfolio claims in standard OAuth 2.0 / OpenID Connect (OIDC) tokens, while each relying party applies its own sufficiency policy - the IdP transports claims and may evaluate an RP-supplied evidence policy for consent, but does not adjudicate access. Enrollment depth varies by modality (some paths are user-initiated; org KYB and officer binding are operator-assisted). xChk also supports human-in-the-loop attestation for high-risk actions: humans can initiate attestations directly (browser UI / POST /api/attestations), and AI agents acting under those principals can trigger the same gateway via scope-gated authorize/attest - hash-chained human approvals on a shared verification graph (humans via OIDC; agents via API keys). A production deployment at https://in.xchk.io ships both initiation paths with bilateral RP evaluation at consent; one documented relying party (https://crabbyed.com, Appendix B) exercises Login with xChk.

Sean MacGuire · 0 citations
Preprint Aug 2026

China RealDID: Verifiable Credentials Anchored in Legal Identity

Verifiable credentials (VCs) and decentralized identifiers (DIDs) enable selective disclosure but lack legal anchoring: without a trusted identity root, verifiers cannot distinguish a genuine holder from a fabricated identity. State identity systems provide biometric-grounded verification but impose three costs: verifiers must collect subjects'full personally identifiable information, infrastructure concentrates on a single API, and the state observes every transaction. We present China RealDID, a three-layer architecture -- CTID (centralized legal identity), RealDID (decentralized anchor on an open permissioned blockchain), and VCs with SD-JWT-based selective disclosure -- evaluated against five adversary classes and six security goals. The central mechanism is a content-blind government relay: the state authenticates participants and counter-signs every credential but cannot read the payload, encrypted by the issuer to the holder's public key. We describe the VC lifecycle, triple-signature chain, open template registry, and the architecture's metadata-level privacy limits, including the credential graph at the relay and presentation linkability from single-DID reuse. The design yields an asymmetric, state-bounded trust model: the state cannot impersonate or read contents; the user cannot fabricate identity or evade metadata observation. We analyze alignment with China's Personal Information Protection Law and the EU's GDPR, including the tension between immutable registries and erasure rights, and discuss generalizability through cross-border deployments with Singapore and Hong Kong.

Yifan He · 0 citations

On the Privacy-Preserving Capabilities of PAVE Specifications in Learnware ∗

This paper formalizes two specification-induced risks in the learnware paradigm and shows that the resulting DP guarantees control both disclosure risk and amplification risk, and analyzes the induced privacy–utility trade-off to guide effective learn-ware identification while preserving privacy.

Hao-Yi Lei, Jin-Hui Wu, Zhi-Hao Tan et al. · 0 citations
#artificial intelligence Preprint Aug 2026

Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification

A privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment and demonstrates that token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting.

Cameron Wilding, Mina Shaker, Fatemeh Ganji · 0 citations