Deep Learning Inferences with Hybrid Homomorphic Encryption

Anthony Meehan, Ryan K L Ko, Geoff Holmes

Abstract: When deep learning is applied to sensitive data sets, many privacy-related implementation issues arise. These issues are especially evident in the healthcare, finance, law and government industries. Homomorphic encryption could allow a server to make inferences on inputs encrypted by a client, but to our best knowledge, there has been no complete implementation of common deep learning operations, for arbitrary model depths, using homomorphic encryption. This paper demonstrates a novel approach, efficiently implementing many deep learning functions with bootstrapped homomorphic encryption. As part of our implementation, we demonstrate Single and Multi-Layer Neural Networks, for the Wisconsin Breast Cancer dataset, as well as a Convolutional Neural Network for MNIST. Our results give promising directions for privacy-preserving representation learning, and the return of data control to users.

TL;DR: We made a feature-rich system for deep learning with encrypted inputs, producing encrypted outputs, preserving privacy.

Keywords: deep learning, homomorphic encryption, hybrid homomorphic encryption, privacy preserving, representation learning, neural networks