论文标题
基于添加性同态加密的深度神经网络，用于非对称协作机器学习
Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning
论文作者
论文摘要
金融部门提供了许多应用各种机器学习技术的机会。集中的机器学习创建了一个限制，从而限制了财务部门的进一步应用。数据隐私是针对各种金融和保险应用程序的基本挑战，这些财务和保险应用程序是在不同部分学习模型的方面。在本文中，我们定义了一个合作的机器学习的新实用方案，该方案一个方拥有数据，但另一方仅拥有标签，并称此\ textbf {非对称合作的机器学习}。对于此方案，我们提出了一种新颖的隐私建筑，在该建筑中，两个方可以在保留各方数据的隐私的同时，有效地协作培训深度学习模型。更具体地说，我们将神经网络的正向传播和反向传播分解为四个不同的步骤，并提出了一种新的协议，以处理这些步骤中的信息泄漏。我们在不同数据集上进行的广泛实验表明，与最先进的系统相比，与准确性损失相比，不仅稳定训练，而且还表明了超过100倍的速度。
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.
