面向用户持有数据的联邦学习实用安全聚合
Practical Secure Aggregation for Federated Learning on User-Held Data
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal 等 9 位作者
AI 速览：为移动设备上用户持有数据的联邦学习设计一种通信高效、可容忍三分之一用户中途失败的高维数据安全聚合协议，以保护每个用户的模型梯度。
Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregation protects each user's model gradient. We design a novel, communication-efficient Secure Aggregation protocol for high-dimensional data that tolerates up to 1/3 users failing to complete the protocol. For 16-bit input values, our protocol offers 1.73x communication expansion for $2^{10}$ users and $2^{20}$-dimensional vectors, and 1.98x expansion for $2^{14}$ users and $2^{24}$ dimensional vectors.