Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning

TL;DR

This paper introduces a privacy-preserving deep neural network training scheme for asymmetrically collaborative machine learning in finance, utilizing additively homomorphic encryption to ensure data privacy and achieve significant speedup.

Contribution

It proposes a novel architecture and protocol for efficient, privacy-preserving collaborative neural network training between parties with asymmetric data ownership.

Findings

Stable training without accuracy loss

Over 100 times speedup compared to existing systems

Effective privacy preservation during training

Abstract

The financial sector presents many opportunities to apply various machine learning techniques. Centralized machine learning creates a constraint which limits further applications in finance sectors. Data privacy is a fundamental challenge for a variety of finance and insurance applications that account on learning a model across different sections. In this paper, we define a new practical scheme of collaborative machine learning that one party owns data, but another party owns labels only, and term this \textbf{Asymmetrically Collaborative Machine Learning}. For this scheme, we propose a novel privacy-preserving architecture where two parties can collaboratively train a deep learning model efficiently while preserving the privacy of each party's data. More specifically, we decompose the forward propagation and backpropagation of the neural network into four different steps and propose a novel protocol to handle information leakage in these steps. Our extensive experiments on different datasets demonstrate not only stable training without accuracy loss, but also more than 100 times speedup compared with the state-of-the-art system.