Bayesian-based Security Distributed Estimation

Abstract

In recent years, the distributed estimation of wireless sensor networks has been widely studied, but there are often security threats in practical applications. For example, attackers damage data information in different ways and reduce the performance of network estimation. In order to solve this problem, this paper proposes an algorithm framework of attack detection based on distributed LMS. The algorithm classifies the states of adjacent nodes, and then realizes attack detection through Bayesian criterion. An adaptive detection threshold is proposed to improve the detection performance. The reliable information of the last time is used to replace the detected lossy information and fuse to ensure the performance of the algorithm. Finally, the simulation results of several algorithms under different attack models are given to prove the effectiveness of the algorithm.