Secure Quantized Training for Deep Learning

Abstract

We implement training of neural networks in secure multi-party computation (MPC) using quantization commonly used in said setting. We are the first to present an MNIST classifier purely trained in MPC that comes within 0.2 percent of the accuracy of the same convolutional neural network trained via plaintext computation. More concretely, we have trained a network with two convolutional and two dense layers to 99.2% accuracy in 3.5 hours (under one hour for 99% accuracy). We have also implemented AlexNet for CIFAR-10, which converges in a few hours. We develop novel protocols for exponentiation and inverse square root. Finally, we present experiments in a range of MPC security models for up to ten parties, both with honest and dishonest majority as well as semi-honest and malicious security.

arXiv comment27 pages

References in corpus (8)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• On the Convergence of Adam and Beyond
• Binarized Neural Networks
• A generic framework for privacy preserving deep learning
• Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications
• Private Machine Learning in TensorFlow using Secure Computation
• secureTF: A Secure TensorFlow Framework
• Effectiveness of MPC-friendly Softmax Replacement