论文标题
同态加密对训练联合学习生成对抗网络的绩效的影响
Effect of Homomorphic Encryption on the Performance of Training Federated Learning Generative Adversarial Networks
论文作者
论文摘要
生成对抗网络（GAN）是机器学习领域（ML）中的深度学习生成模型，涉及使用相当大的数据集训练两个神经网络（NN）。在某些领域，例如医学领域，培训数据可能是在不同医院中存储的医院患者记录。经典的集中式方法将涉及将数据发送到将训练该模型的集中式服务器。但是，这将涉及违反患者及其数据的隐私和机密性，这是不可接受的。因此，联合学习（FL）是一种在没有数据离开主机设备的情况下在分布式设置中训练ML模型的ML技术，将是集中选项的更好替代方法。在这种ML技术中，只能传达参数和某些元数据。尽管如此，仍然存在使用参数和元数据推断用户数据的攻击。完全保密的解决方案涉及传达数据的同型加密（HE）。本文将重点介绍具有三种不同类型的同态加密的FL-GAN的性能丧失：部分同型加密（PHE），有点同构加密（SHE）和完全同构加密（FHE）。我们还将测试多方计算（MPC）的性能损失，因为它具有同构特性。表演将与无加密的FL-GAN的性能进行比较。我们的实验表明，加密方法越复杂，与FL的基本情况相比，他花费的额外时间非常重要。
A Generative Adversarial Network (GAN) is a deep-learning generative model in the field of Machine Learning (ML) that involves training two Neural Networks (NN) using a sizable data set. In certain fields, such as medicine, the training data may be hospital patient records that are stored across different hospitals. The classic centralized approach would involve sending the data to a centralized server where the model would be trained. However, that would involve breaching the privacy and confidentiality of the patients and their data, which would be unacceptable. Therefore, Federated Learning (FL), an ML technique that trains ML models in a distributed setting without data ever leaving the host device, would be a better alternative to the centralized option. In this ML technique, only parameters and certain metadata would be communicated. In spite of that, there still exist attacks that can infer user data using the parameters and metadata. A fully privacy-preserving solution involves homomorphically encrypting (HE) the data communicated. This paper will focus on the performance loss of training an FL-GAN with three different types of Homomorphic Encryption: Partial Homomorphic Encryption (PHE), Somewhat Homomorphic Encryption (SHE), and Fully Homomorphic Encryption (FHE). We will also test the performance loss of Multi-Party Computations (MPC), as it has homomorphic properties. The performances will be compared to the performance of training an FL-GAN without encryption as well. Our experiments show that the more complex the encryption method is, the longer it takes, with the extra time taken for HE is quite significant in comparison to the base case of FL.
