论文标题
安全总和优于（当前）协作深度学习中的同态加密
Secure Sum Outperforms Homomorphic Encryption in (Current) Collaborative Deep Learning
论文作者
论文摘要
深度学习（DL）方法正在在广泛的领域中取得非凡的结果，但通常需要大量的私人数据收集。因此，需要培训神经网络的方法，以使各方的输入机密的不同数据所有者的联合数据进行培训。我们解决了联合学习中的特定环境，即从水平分布的数据中进行有限的当事方进行深入学习的设置，其中必须以隐私的方式处理其脆弱的中级结果。该环境可以在医疗和医疗保健以及工业应用中找到。这样做的主要方案是基于同态加密（HE），并且被广泛认为是没有其他选择的。与此相反，我们证明了一个经过精心选择的，不太复杂和计算较低的安全总和协议与默认的安全通道相结合，就勾结抗性和运行时而言，具有出色的属性。最后，我们在协作DL的背景下讨论了几个开放研究问题，尤其是关于由联合中间结果引起的隐私风险。
Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection of private data. Hence, methods for training neural networks on the joint data of different data owners, that keep each party's input confidential, are called for. We address a specific setting in federated learning, namely that of deep learning from horizontally distributed data with a limited number of parties, where their vulnerable intermediate results have to be processed in a privacy-preserving manner. This setting can be found in medical and healthcare as well as industrial applications. The predominant scheme for this is based on homomorphic encryption (HE), and it is widely considered to be without alternative. In contrast to this, we demonstrate that a carefully chosen, less complex and computationally less expensive secure sum protocol in conjunction with default secure channels exhibits superior properties in terms of both collusion-resistance and runtime. Finally, we discuss several open research questions in the context of collaborative DL, especially regarding privacy risks caused by joint intermediate results.
