A Privacy-Preserving Asynchronous Averaging Algorithm based on Shamir’s Secret Sharing
Qiongxiu Li, Mads Græsbøll Christensen · 2019
Average consensus is widely used in information fusion, and it requires information exchange between a set of nodes to achieve an agreement. Unfortunately, the information exchange may disclose the individual's private information, and this raises serious concerns for individual privacy in some applications. Hence, a privacy-preserving asynchronous averaging algorithm is proposed in this paper to maintain the privacy of each individual using Shamir's secret sharing scheme, as known from secure multiparty computation. The proposed algorithm is based on a lightweight cryptographic technique. It gives identical accuracy solution as the non-privacy concerned algorithm and achieves perfect security in clique-based networks without the use of a trusted third party. In each iteration of the algorithm, each individual's privacy in the selected clique is protected under a passive attack where the adversary controls some of the nodes. Finally, it also achieves robustness of up to one third transmission error.