Secure Quantized Training for Deep Learning
This addresses the problem of secure and private deep learning training for scenarios requiring data confidentiality, though it is incremental as it builds on existing MPC and quantization techniques.
The paper tackles the problem of training neural networks securely using multi-party computation (MPC) with quantization, achieving a result where an MNIST classifier trained in MPC reaches within 0.2% accuracy of plaintext training, specifically 99.2% accuracy in 3.5 hours.
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.