Ecole d'ingénieur et centre de recherche en Sciences du numérique

Embedded proofs for verifiable neural networks

Chabanne, Hervé; Keuffer, Julien; Molva, Refik

Cryptology ePrint Archive: Report 2017/1038, October 2017

The increasing use of machine learning algorithms to deal with large amount of data and the expertise required by these algorithms lead users to outsource machine learning services. This raises a trust issue about their result when executed in an untrusted environment. Verifiable computing (VC) tackles this issue and provides computational integrity for an outsourced computation, although the bottleneck of state of the art VC protocols is the prover time. In this paper, we design a VC protocol tailored to verify a sequence of operations for which existing VC schemes do not perform well on \emph the operations. We thus suggest a technique to compose several specialized and efficient VC schemes with Parno et al.'s general purpose VC protocol Pinocchio, by integrating the verification of the proofs generated by these specialized schemes as a function that is part of the sequence of operations verified using Pinocchio. The resulting scheme keeps Pinocchio's property while being more efficient for the prover. Our scheme relies on the underlying cryptographic assumptions of the composed protocols for correctness and soundness.

Document Bibtex

Titre:Embedded proofs for verifiable neural networks
Mots Clés:verifiable computation, proof composition, neural networks
Type:Rapport
Langue:English
Ville:
Date:
Département:Sécurité numérique
Eurecom ref:5400
Copyright: IACR
Bibtex: @techreport{EURECOM+5400, year = {2017}, title = {{E}mbedded proofs for verifiable neural networks}, author = {{C}habanne, {H}erv{\'e} and {K}euffer, {J}ulien and {M}olva, {R}efik}, number = {EURECOM+5400}, month = {10}, institution = {Eurecom}, url = {http://www.eurecom.fr/publication/5400},, }
Voir aussi: