Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs

Deep Learning as a Service (DLaaS) stands as a promising solution for cloud-based inference applications. In this setting, the cloud has a pre-learned model whereas the user has samples on which she wants to run the model. The biggest concern with DLaaS is user privacy if the input samples are sensi...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Ahmad Al Badawi, Chao, Jin, Lin, Jie, Chan, Fook Mun, Sim, Jun Jie, Benjamin Hong Meng Tan, Xiao, Nan, Khin Mi Mi Aung, Vijay Ramaseshan Chandrasekhar
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 18.08.2020
Subjects
Cloud computing
Computing costs
Cybersecurity
Encryption
Image classification
Levels
Machine learning
Training
Virtual networks
Online AccessGet full text

Cover

More Information
Summary:Deep Learning as a Service (DLaaS) stands as a promising solution for cloud-based inference applications. In this setting, the cloud has a pre-learned model whereas the user has samples on which she wants to run the model. The biggest concern with DLaaS is user privacy if the input samples are sensitive data. We provide here an efficient privacy-preserving system by employing high-end technologies such as Fully Homomorphic Encryption (FHE), Convolutional Neural Networks (CNNs) and Graphics Processing Units (GPUs). FHE, with its widely-known feature of computing on encrypted data, empowers a wide range of privacy-concerned applications. This comes at high cost as it requires enormous computing power. In this paper, we show how to accelerate the performance of running CNNs on encrypted data with GPUs. We evaluated two CNNs to classify homomorphically the MNIST and CIFAR-10 datasets. Our solution achieved a sufficient security level (> 80 bit) and reasonable classification accuracy (99%) and (77.55%) for MNIST and CIFAR-10, respectively. In terms of latency, we could classify an image in 5.16 seconds and 304.43 seconds for MNIST and CIFAR-10, respectively. Our system can also classify a batch of images (> 8,000) without extra overhead.
ISSN:2331-8422