ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2020

ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing

Abstract

We propose ARIANN, a low-interaction framework to perform private training and inference of standard deep neural networks on sensitive data. This framework implements semi-honest 2-party computation and leverages function secret sharing, a recent cryptographic protocol that only uses lightweight primitives to achieve an efficient online phase with a single message of the size of the inputs, for operations like comparison and multiplication which are building blocks of neural networks. Built on top of PyTorch, it offers a wide range of functions including ReLU, MaxPool and BatchNorm, and allows to use models like AlexNet or ResNet18. We report experimental results for inference and training over distant servers. Last, we propose an extension to support n-party private federated learning.
Fichier principal
Vignette du fichier
2006.04593.pdf (634.54 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-02896127 , version 1 (10-07-2020)

Identifiers

  • HAL Id : hal-02896127 , version 1

Cite

Théo Ryffel, David Pointcheval, Francis Bach. ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing. 2020. ⟨hal-02896127⟩
1008 View
165 Download

Share

Gmail Mastodon Facebook X LinkedIn More