The AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data with GPUs
Institute for Infocomm Research, A*STAR, Singapore
arXiv:1811.00778 [cs.CR], (2 Nov 2018)
@article{badawi2018alexnet,
title={The AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data with GPUs},
author={Al Badawi, Ahmad and Chao, Jin and Lin, Jie and Mun, Chan Fook and Jie, Sim Jun and Tan, Benjamin Hong Meng and Nan, Xiao and Aung, Khin Mi Mi and Chandrasekhar, Vijay Ramaseshan},
year={2018},
month={nov},
archivePrefix={"arXiv"},
primaryClass={cs.CR}
}
Fully homomorphic encryption, with its widely-known feature of computing on encrypted data, empowers a wide range of privacy-concerned cloud applications including deep learning as a service. This comes at a high cost since FHE includes highly-intensive computation that requires enormous computing power. Although the literature includes a number of proposals to run CNNs on encrypted data, the performance is still far from satisfactory. In this paper, we push the level up and show how to accelerate the performance of running CNNs on encrypted data using GPUs. We evaluated a CNN to classify homomorphically the MNIST dataset into 10 classes. We used a number of techniques such as low-precision training, unified training and testing network, optimized FHE parameters and a very efficient GPU implementation to achieve high performance. Our solution achieved high security level (> 128 bit) and high accuracy (99%). In terms of performance, our best results show that we could classify the entire testing dataset in 14.105 seconds, with per-image amortized time (1.411 milliseconds) 40.41x faster than prior art.
November 11, 2018 by hgpu
