Privacy-Preserving Distributed Average Consensus based on Additive Secret Sharing

Qiongxiu Li, Ignacio Cascudo, Mads Græsbøll Christensen

Abstract: One major concern of distributed computation in networks is the privacy of the individual nodes. To address this privacy issue in the context of the distributed average consensus problem, we propose a general, yet simple solution that achieves privacy using additive secret sharing, a tool from secure multiparty computation. This method enables each node to reach the consensus accurately and obtains perfect security at the same time. Unlike differential privacy based approaches, there is no trade-off between privacy and accuracy. Moreover, the proposed method is computationally simple compared to other techniques in secure multiparty computation, and it is able to achieve perfect security of any honest node as long as it has one honest neighbour under the honest-but-curious model, without any trusted third party.