A verification framework for secure machine learning - Archive ouverte HAL Access content directly
Conference Papers Year :

A verification framework for secure machine learning

(1) , (1)
1

Abstract

We propose a programming and verification framework to help developers build distributed software applications using composite homomorphic encryption (and secure multi-party computation) protocols, and implement secure machine learning and classification over private data. With our framework, a developer can prove that the application code is functionally correct, that it correctly composes the various cryptographic schemes it uses, and that it does not accidentally leak any secrets (via side-channels, for example.) Our end-to-end solution results in verified and efficient implementations of state-of-the-art secure privacy-preserving learning and classification techniques.
Fichier principal
Vignette du fichier
paper-ppml19.pdf (641.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03465963 , version 1 (04-12-2021)

Identifiers

  • HAL Id : hal-03465963 , version 1

Cite

Prasad Naldurg, Karthikeyan Bhargavan. A verification framework for secure machine learning. Privacy preserving machine learning Virtual ACM CCS 2021 Workshop, Nov 2019, London / Virtual, United Kingdom. ⟨hal-03465963⟩
39 View
37 Download

Share

Gmail Facebook Twitter LinkedIn More