A generic framework for privacy preserving deep learning

TL;DR

This paper introduces a versatile framework for privacy-preserving deep learning that supports multiple privacy techniques and maintains a familiar API, enabling secure data processing with minimal accuracy impact.

Contribution

It presents the first reliable, general framework for privacy-preserving deep learning integrating federated learning, secure computation, and differential privacy.

Findings

Privacy features do not affect prediction accuracy (except Differential Privacy).

Framework introduces performance overhead that will be optimized later.

Early results show promising applicability on standard datasets.

Abstract

We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valuable representation based on chains of commands and tensors. This abstraction allows one to implement complex privacy preserving constructs such as Federated Learning, Secure Multiparty Computation, and Differential Privacy while still exposing a familiar deep learning API to the end-user. We report early results on the Boston Housing and Pima Indian Diabetes datasets. While the privacy features apart from Differential Privacy do not impact the prediction accuracy, the current implementation of the framework introduces a significant overhead in performance, which will be addressed at a later stage of the development. We believe this work is an important milestone introducing the first reliable, general framework for privacy preserving deep learning.