Secure Distributed Estimation Over Wireless Sensor Networks Under Attacks

The problem of distributed estimation over wireless sensor networks in an adversarial environment with the presence of attacks on sensed and communicated information is considered. To tackle with this problem, a secure diffusion least-mean squares (S-dLMS) algorithm is proposed. The proposed S-dLMS can be considered as a hybrid system, which consists of a noncooperative LMS (nc-LMS) subsystem and a diffusion LMS (dLMS) subsystem. The nc-LMS subsystem is used to provide a reliable reference estimate, which is further used for constructing the threshold test to detect the trust neighbors of each node. Then, based on the detected secure network topology, the dLMS subsystem is performed by combining the received information from the trust neighbors. The performance of the proposed S-dLMS algorithm in the mean and mean-square senses is analyzed, and then an adaptive rule is suggested to select the threshold for detection. Finally, some simulations are performed to show the effectiveness of the proposed S-dLMS algorithm under fixed and time-varying attacks, respectively.