Source · Tier A · Peer-reviewed

NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs

Z. Wang. 2026. International Conference on Information and Communications Security (ICICS 2026).

Originalhttps://arxiv.org/abs/2603.18046
DOI10.48550/arXiv.2603.18046
arXiv2603.18046
VersionCurrent arXiv HTML read on 2026-09-25; its abstract matches v2, which states acceptance at the 28th ICICS (Springer LNCS, Fukui, 27–30 October 2026) and is an extended version with appendices not in the proceedings. v1 (March 2026) reports different timings. The abstract gives 3.5–3.7 KB per sub-circuit proof, while §3.1 and §6.1 give 3.2–3.7 KB.
Accessed2026-09-25
Imported fromhodgkins-ai-verification-papers@c71e59ff0e8e
NoteListed under "Zero-knowledge proofs" in the Hodgkins bibliography (CC BY 4.0).

Cited by

Search

Full search page