An intelligent cognitive computing based intrusion detection for industrial cyber-physical systems

Abstract

Advanced developments of Industrial Cyber-Physical Systems (CPSs), comprising Internet of Things (IoT) finds useful in several application areas such as transportation, smart cities, healthcare, energy distribution, agriculture, etc. At the same time, the increased utilization of industrial CPS offers many threats which could have major significances for users. Recently, cognitive computing and artificial intelligence techniques offer new opportunities for the revolution of industrial CPSs. Therefore, to achieve security in industrial CPS, AI based intrusion detection system (IDS) can be developed to detect anomalies and prevent their harmful effects. With this motivation, this paper presents a novel cognitive computing based IDS technique to achieve security in industrial CPS. The proposed model involves different stages of operations such as data acquisition, preprocessing, feature selection, classification, and parameter optimization. The proposed model involves preprocessing to discard the noise that exists in the data. Then, the presented model uses binary bacterial foraging optimization (BBFO) based feature selection technique to elect an optimal subset of features. Besides the gated recurrent unit (GRU) model is applied to identify the presence of intrusions in the industrial CPS environment. Finally, Nesterov-accelerated Adaptive Moment Estimation (NADAM) optimizer is applied for the hyperparameter optimization of the GRU model in such a way that the detection rate can be enhanced. In order to validate the performance of the BBFO-GRU model, a series of experiments were carried out using the data from industrial CPS and the resultant values highlighted the promising performance of the proposed model with an accuracy of 98.45%.