Artificial intelligence driven cyberattack detection system using integration of deep belief network with convolution neural network on industrial IoT

In Industry 4.0, information and communication technology (ICT) was employed in numerous significant infrastructures, like financial networks, smart factories, and power plants, to automate and certify industrial systems. In power control systems, ICT technologies such as IIoT have improved automated monitoring, but legacy methods, originally autonomous, now connect with external networks. This progress has presented safety vulnerabilities from legacy ICT systems. Hence, various cybersecurity approaches are developed and examined to deal with cyberattacks and vulnerabilities. Utilizing new cybersecurity models in power control systems poses risks due to their uncertified safety. Ensuring their stability and efficiency is significant for maintaining reliable power delivery and incorporating these technologies into power control systems. Therefore, this study designs a Next–Generation Cybersecurity Attack Detection using an ensemble deep learning model (NGCAD-EDLM) technique in the IIoT environment. The main cause of the NGCAD-EDLM technique is the automatic recognition of cyber-attacks. In the NGCAD-EDLM approach, the primary data normalization phase utilizing min-max normalization is performed. Next, the honey-badger algorithm (HBA) approach selects the feature subsets. Furthermore, an ensemble deep learning (DL) of two methods, namely convolutional neural networks (CNNs) and deep belief networks (DBNs) methods, are employed for classification. In addition, the DL techniques' hyperparameter selection is accomplished using the lotus effect optimization algorithm (LEOA) method. A complete set of simulation validation is performed to establish the experimental analysis of the NGCAD-EDLM method. The performance validation of the NGCAD-EDLM method exhibited a superior accuracy value of 99.21 % over other existing techniques.