Voting-based ensemble classifiers model on ransomware detection for cybersecurity driven iiot in cloud computing infrastructure

Abstract

The smart factory environment was converted into an Industrial Internet of Things (IIoT) environment because it is an open approach and interconnected. This has made smart manufacturing plants susceptible to cyberattacks and has openly led to real damage. Many cyberattacks targeting smart factories were controlled using malware. So, a solution that effectively identifies malware by analyzing and monitoring network traffic for malware threats in a smart factory IIoT environment is vital. However, attaining precise real malware recognition in such environments was challenging. Ransomware is a kind of malware that encodes the victim's data and demands payment to restore access. The effective recognition of ransomware attacks is highly based on how its features are learned and how accurately its activities are recognized. This article proposes a Voting-Based Ensemble Classifiers Model on Ransomware Detection for Cybersecurity (VBECM-RDCS) technique for IIoT in cloud computing infrastructure. The VBECM-RDCS technique utilizes the squirrel search algorithm (SSA) model for feature subset selection. Furthermore, a voting ensemble classifier for ransomware detection employs the convolutional autoencoder (CAE) integrated with bidirectional gated recurrent unit (Bi-GRU). Finally, the walrus optimization algorithm (WAOA) model is implemented for optimum hyperparameter tuning to improve the recognition performance of ensemble methods. The simulation study of the VBECM-RDCS technique is examined under the ransomware detection dataset. The VBECM-RDCS technique attained a superior accuracy value of 99.76 % under 2000 training epochs, outperforming existing models in the experimental evaluation.