Metraipolis › archive › dc_83a0f433e022

Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees — arXiv:2608.17070

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.17070
License (as archived)
CC0-1.0
Archived
2026-10-18T14:48:26.693Z
SHA-256 of the archived text
ca14046367959423996dc08f80f162f4c36736988fd40b4d8e797cc04aa419c6
Stable URL of this page
https://metraipolis.com/documento/dc_83a0f433e022

How to cite

Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees — arXiv:2608.17070 — arXiv (en), https://arxiv.org/abs/2608.17070 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83a0f433e022 (Metraipolis archive dc_83a0f433e022, sha256 ca14046367959423996dc08f80f162f4c36736988fd40b4d8e797cc04aa419c6)
BibTeX
@misc{dc83a0f433e022,
  title = {Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees — arXiv:2608.17070},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17070},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83a0f433e022; sha256 ca14046367959423996dc08f80f162f4c36736988fd40b4d8e797cc04aa419c6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17070. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings. However, model parameters are often commercial secrets that cannot be disclosed to auditors or end users. To this end, we present PANDA, a scalable system that uses zero-knowledge proofs (ZKPs) to prove the robustness and fairness properties of a model without revealing its private parameters. PANDA is built on top of CROWN, an efficient robustness certification framework that is used in many state-of-the-art formal verification tools for neural networks. The core contribution of PANDA is a novel algorithm for proving linear relaxation bounds for non-linear activation layers, yielding simple, lightweight proofs. Remarkably, our system can generate proofs of local robustness for neural networks with more than 2.9M parameters in 5 minutes, and can verify them in 10 seconds. Prior ZKP-based robustness system rely on exponential-time algorithms that cannot scale to nontrivial networks. In contrast, PANDA scales polynomially in the number of neurons in a network, allowing us to support neural networks 4 orders of magnitude larger than previous approaches with significantly reduced prover overhead.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2608.17070 — 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 2026-10-18T14:47:59.376Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).