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

06/08/2020
by   Theo Ryffel, et al.
6

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/10/2021

Practical Two-party Privacy-preserving Neural Network Based on Secret Sharing

Neural networks, with the capability to provide efficient predictive mod...
research
02/07/2022

CECILIA: Comprehensive Secure Machine Learning Framework

Since machine learning algorithms have proven their success in data mini...
research
04/22/2021

CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU

We introduce CryptGPU, a system for privacy-preserving machine learning ...
research
01/28/2021

S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training

We introduce S++, a simple, robust, and deployable framework for trainin...
research
08/21/2022

Efficient Multiparty Protocols Using Generalized Parseval's Identity and the Theta Algebra

We propose a protocol able to show publicly addition and multiplication ...
research
02/05/2023

RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference

The proliferation of deep learning (DL) has led to the emergence of priv...
research
01/10/2018

Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications

We present Chameleon, a novel hybrid (mixed-protocol) framework for secu...

Please sign up or login with your details

Forgot password? Click here to reset