Hybrid Metaheuristics Feature Selection with Stacked Deep Learning-Enabled Cyber-Attack Detection Model

Abstract

Due to exponential increase in smart resource limited devices and high speed communication technologies, Internet of Things (IoT) have received significant attention in different application areas. However, IoT environment is highly susceptible to cyber-attacks because of memory, processing, and communication restrictions. Since traditional models are not adequate for accomplishing security in the IoT environment, the recent developments of deep learning (DL) models find beneficial. This study introduces novel hybrid metaheuristics feature selection with stacked deep learning enabled cyber-attack detection (HMFS-SDLCAD) model. The major intention of the HMFS-SDLCAD model is to recognize the occurrence of cyberattacks in the IoT environment. At the preliminary stage, data pre-processing is carried out to transform the input data into useful format. In addition, salp swarm optimization based on particle swarm optimization (SSOPSO) algorithm is used for feature selection process. Besides, stacked bidirectional gated recurrent unit (SBiGRU) model is utilized for the identification and classification of cyberattacks. Finally, whale optimization algorithm (WOA) is employed for optimal hyperparameter optimization process. The experimental analysis of the HMFS-SDLCAD model is validated using benchmark dataset and the results are assessed under several aspects. The simulation outcomes pointed out the improvements of the HMFS-SDLCAD model over recent approaches.