神经网络量化以加速同态加密
Neural Network Quantisation for Faster Homomorphic Encryption
AI总结：
本研究通过量化感知训练减小神经网络整数位宽，在BFV同态加密方案下分别将MNIST和CIFAR网络执行时间减少80%和40%，同时保持精度。
AI中文摘要：
同态加密（HE）使得在加密数据上进行计算成为可能，从而能够执行保护隐私的神经网络推理。该技术的一个缺点是，其速度比在未加密数据上计算慢几个数量级。神经网络通常使用浮点数进行训练，而大多数同态加密库在整数上计算，因此需要对神经网络进行量化。一种直接的方法是量化到大整数（例如32位）以避免大的量化误差。在这项工作中，我们使用量化感知训练来减小网络的整数大小，以实现更高效的计算。对于Badawi等人提出的目标MNIST架构，我们将整数大小减少了33%，且精度没有显著损失；而对于CIFAR架构，我们可以将整数大小减少43%。在使用SEAL库的BFV同态加密方案下实现所得网络，我们能够将MNIST神经网络的执行时间减少80%，将CIFAR神经网络的执行时间减少40%。
英文摘要：
Homomorphic encryption (HE) enables calculating on encrypted data, which makes it possible to perform privacypreserving neural network inference. One disadvantage of this technique is that it is several orders of magnitudes slower than calculation on unencrypted data. Neural networks are commonly trained using floating-point, while most homomorphic encryption libraries calculate on integers, thus requiring a quantisation of the neural network. A straightforward approach would be to quantise to large integer sizes (e.g. 32 bit) to avoid large quantisation errors. In this work, we reduce the integer sizes of the networks, using quantisation-aware training, to allow more efficient computations. For the targeted MNIST architecture proposed by Badawi et al., we reduce the integer sizes by 33% without significant loss of accuracy, while for the CIFAR architecture, we can reduce the integer sizes by 43%. Implementing the resulting networks under the BFV homomorphic encryption scheme using SEAL, we could reduce the execution time of an MNIST neural network by 80% and by 40% for a CIFAR neural network.
