Secret Sharing Sharing For Highly Scalable Secure Aggregation

TL;DR

This paper introduces a highly efficient secure aggregation protocol for federated learning that uses group-based secret sharing with sharding, achieving sub-linear communication complexity and scalability to 100 million clients.

Contribution

It presents a novel group-based secret sharing protocol with sharding that significantly improves communication and computation efficiency in secure aggregation.

Findings

Supports secure aggregation with 100 million clients.

Achieves less than 0.5 seconds server computation time.

Requires only 350 client communications per participant.

Abstract

Secure Multiparty Computation (MPC) can improve the security and privacy of data owners while allowing analysts to perform high quality analytics. Secure aggregation is a secure distributed mechanism to support federated deep learning without the need for trusted third parties. In this paper we present a highly performant secure aggregation protocol with sub-linear communication complexity. Our protocol achieves greater communication and computation efficiencies through a group-based approach. It is similar to secret sharing protocols extended to vectors of values-aka gradients-but within groups we add an additional layer of secret sharing of shares themselves-aka sharding. This ensures privacy of secret inputs in the standard real/ideal security paradigm, in both semi-honest and malicious settings where the server may collude with the adversary. In the malicious setting with 5% corrupt clients and 5% dropouts, our protocol can aggregate over a federation with 100,000,000 members and vectors of length 100 while requiring each client to communicate with only 350 other clients. The concrete computation cost for this aggregation is less than half a second for the server and less than 100ms for the client.