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

TL;DR

ARIANN introduces a lightweight, efficient privacy-preserving framework for neural network training and inference using function secret sharing, optimized primitives, and GPU acceleration, enabling secure computation on sensitive data with reduced communication overhead.

Contribution

It presents a novel low-interaction protocol for private neural network operations leveraging function secret sharing and optimized primitives, supporting both two-party and multi-party federated learning.

Findings

Efficient private inference on standard neural networks like AlexNet and ResNet18.

Reduced communication overhead with smaller preprocessing keys.

GPU acceleration significantly improves computation speed.

Abstract

We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. Our semi-honest 2-party computation protocol (with a trusted dealer) leverages function secret sharing, a recent lightweight cryptographic protocol that allows us to achieve an efficient online phase. We design optimized primitives for the building blocks of neural networks such as ReLU, MaxPool and BatchNorm. For instance, we perform private comparison for ReLU operations with a single message of the size of the input during the online phase, and with preprocessing keys close to 4X smaller than previous work. Last, we propose an extension to support n-party private federated learning. We implement our framework as an extensible system on top of PyTorch that leverages CPU and GPU hardware acceleration for cryptographic and machine learning operations. We evaluate our end-to-end system for private inference between distant servers on standard neural networks such as AlexNet, VGG16 or ResNet18, and for private training on smaller networks like LeNet. We show that computation rather than communication is the main bottleneck and that using GPUs together with reduced key size is a promising solution to overcome this barrier.