SEALion: a Framework for Neural Network Inference on Encrypted Data

TL;DR

SEALion is an extensible framework enabling privacy-preserving neural network inference on encrypted data, combining TensorFlow and homomorphic encryption for secure machine learning applications.

Contribution

It introduces a flexible framework that simplifies training and inference of neural networks on encrypted data, with novel features like activity sparsification and encrypted transfer learning.

Findings

Enhanced inference efficiency via activity sparsifier

Successful encrypted transfer learning with Variational AutoEncoder

Framework supports seamless prototyping with security abstraction

Abstract

We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework consists of two layers: the first is built upon TensorFlow and SEAL and exposes standard algebra and deep learning primitives; the second implements a Keras-like syntax for training and inference with neural networks. Given a required level of security, a user is abstracted from the details of the encoding and the encryption scheme, allowing quick prototyping. We present two applications that exemplifying the extensibility of our proposal, which are also of independent interest: i) improving efficiency of neural network inference by an activity sparsifier and ii) transfer learning by querying a server-side Variational AutoEncoder that can handle encrypted data.