Attack Detection and Optimal Deployment for Underwater Constrained Wireless Sensor Networks via Hybrid Trust Evidence

Abstract

Underwater wireless sensor networks have been widely used in the acquisition and processing of oceanic information. The marine environment is complex and changeable, and the existence of obstacles is the main manifestation of the complex underwater environment, which affect the communication between underwater nodes. In addition, wireless sensor networks with obstacles are often more vulnerable to various attacks, making it more fragile. In order to address the aforementioned issues, we firstly propose a underwater wireless sensor deployment strategy with obstacle avoidance as the target (GEHO). After that, we use Tabtransformer algorithm to build trust model and detect attacks according to trust data set, which can enhance the robustness of the entire wireless sensor network. In the final stage, we collect the patterns of malicious attacks on nodes according to the detection results, which is convenient for us to make timely responses and reduce the losses of underwater acoustic sensor networks due to malicious attacks. The simulation results show that the trust model can effectively detect malicious nodes and attack types in the network, and has higher detection accuracy than the existing trust model.