Year: 2016
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Authors: Bonawitz, Keith, Ivanov, Vladimir, Kreuter, Ben, Marcedone, Antonio, McMahan, H. Brendan, Patel, Sarvar, Ramage, Daniel, Segal, Aaron, Seth, Karn
Institutions: Google (United States), Cornell University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2579186979