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.
翻译:我们用上述环境中常用的量化方法对神经网络进行安全多党计算(MPC)的培训。我们是第一个提出在MPC中纯受过MNIST分类培训的神经网络,其精确度不超过通过平文本计算所培训的同一进化神经网络精度的0.2%。更具体地说,我们用3.5小时(99%的精确度低于1小时)对两个革命层和两个密集层进行了网络培训,精确度达到99.2%。我们还为CIFAR-10安装了AlexNet,这个网络在几个小时内会聚在一起。我们为Expentition和反正方根制定了新的协议。最后,我们为多达10个政党介绍了MPC安全模式的实验,其中多数是诚实和不诚实的,大多数是半诚实和恶意的安全。