BLOCK HUNTER: BLOCKCHAIN-BASED CYBER THREAT DETECTION USING POOLING LEARNING IN IIOT NETWORKS

Abstract

The Industrial Internet of Things (IIoT) is a powerful Internet of Things (IoT) application that transforms industry development by boosting open communication between different entities such as hubs, manufacturing facilities, and packaging facilities. The IIoT can more efficiently analyse obtained data by incorporating data science approaches, which current IIoT systems lack due to their distributed nature. Anomalies and assaults on networks pose a serious security risk for IIoT. In this study, a coordinator IoT device is chosen to calculate the trust of IoT devices in order to prevent fraudulent devices from joining the network. Furthermore, implementing a blockchain-based data paradigm promotes data transparency. The proposed system's effectiveness is completely and meticulously verified using MATLAB against a range of security parameters, including attack strength, message tampering, and false authentication likelihood. The simulation findings show that the proposed strategy increases IIoT network security by effectively identifying hostile network threats.