Cryptology ePrint Archive: Report 2017/281

Practical Secure Aggregation for Privacy Preserving Machine Learning

Keith Bonawitz and Vladimir Ivanov and Ben Kreuter and Antonio Marcedone and H. Brendan McMahan and Sarvar Patel and Daniel Ramage and Aaron Segal and Karn Seth

Abstract: We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and malicious settings, and show that security is maintained even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers $1.73\times$ communication expansion for $2^{10}$ users and $2^{20}$-dimensional vectors, and $1.98\times$ expansion for $2^{14}$ users and $2^{24}$-dimensional vectors over sending data in the clear.

Category / Keywords: cryptographic protocols /

Date: received 27 Mar 2017, last revised 16 Mar 2018

Contact author: karn at google com

Available format(s): PDF | BibTeX Citation

Version: 20180316:163548 (All versions of this report)

Short URL: ia.cr/2017/281