AI Driven False Data Injection Attack Recognition Approach for Cyber-Physical Systems in Smart Cities

Abstract

Cyber-physical systems (CPS) combine the typical power grid with recent communication and control technologies, generating new features for attacks. False data injection attacks (FDIA) contain maliciously injecting fabricated data as to the system measurements, capable of due to improper decisions and disruptions in power distribution. Identifying these attacks is vital for preserving the reliability and integrity of the power grid. Researchers in this domain utilize modern approaches namely machine learning (ML) and deep learning (DL) for detecting anomalous forms in the data that signify the existence of such attacks. By emerging accurate and effective detection approaches, this research purposes to improve the resilience of CPS and make sure of a secure and continuous power supply to consumers. This article presents an Improved Equilibrium Optimizer with Deep Learning Enabled False Data Injection Attack Recognition (IEODL-FDIAR) technique in a CPS platform. The main purpose of the IEODL-FDIAR technique is to enable FDIA attack detection and accomplishes security in the CPSS environment. In the presented IEODL-FDIAR technique, the IEO algorithm is used for the feature subset selection process. Moreover, the IEODL-FDIAR technique applies a stacked autoencoder (SAE) model for FDIA attack detection. Furthermore, the pelican optimization algorithm (POA) can be utilized for the optimum hyperparameter chosen for the SAE algorithm which in turn boosts the detection outcomes of the SAE model. To portray the better outcome of the IEODL-FDIAR system, a wide range of simulation analyses are executed. A wide comparison analysis described the improved results of the IEODL-FDIAR technique with existing DL models.