Privacy-Preserving Dynamic Average Consensus via Random Number Perturbation
Lan Gao, Yiqun Zhou, Xin Chen, Runfeng Cai, Guo Chen, Chaojie Li
Abstract
This brief focuses on the study of privacy preservation of dynamic average consensus (DAC) in multi-agent networks. A privacy-preserving DAC (PP-DAC) algorithm is proposed based on a carefully designed random number perturbation mechanism. The PP-DAC algorithm is able to protect agents from the leakage of sensitive information without compromising their tracking accuracy. Furthermore, the privacy analysis for different scenarios is given to show that the PP-DAC algorithm works well unless all neighbors of the target agent collude with each other to attack this agent. Also, some numerical simulations are given to illustrate the validity of the proposed algorithm.
Topics & Concepts
Computer sciencePerturbation (astronomy)AlgorithmConsensus algorithmTheoretical computer sciencePhysicsQuantum mechanicsDistributed Control Multi-Agent SystemsOpinion Dynamics and Social InfluenceOpportunistic and Delay-Tolerant Networks