Multimodal Sensor Data Fusion Based Cyberattack Detection in Industrial Internet of Things Environment

The Industrial Internet of Things (IIoT) cites the usage of classical Internet of Things (IoT) in different applications and industrial fields. Smart grids, smart homes, supply chain management, connected cars, and smart cities are the different applications of IIoT. But this system is widely targeted by cyber-criminals. Big data analytics and Deep learning (DL) have considerable potential in developing and designing strong security systems for IIoT networks. This manuscript introduces Multimodal Sensor Data Fusion based Cyberattack Detection with glow worm swarm optimization (MSDF-CDGSO) technique in IIoT environment. The MSDF-CDGSO technique examines the IIoT data for identifying the existence of cyberattacks in the IIoT environment. In the presented MSDF-CDGSO technique, the IIoT devices collect data from different devices and fused them together. At the preliminary stage, the MSDF-CDGSO technique preprocesses the input data to scale them properly. For cyberattack detection, the MSDF-CDGSO technique uses class-specific cost regulation extreme learning machine (CCR-ELM) model. Finally, the GSO method is exploited to adjust the parameter values of the CCR-ELM algorithm. The simulation result analysis of the MSDF-CDGSO method is investigated on benchmark database. A widespread comparison results highlighted that the MSDF-CDGSO technique reaches improved cybersecurity in the IIoT environment.