FogNet: Custom CNN with optimal feature selection-based combat model for secured fog computing environment

Abstract

In recent years, the increasing number of connected devices and the exponential growth of data generated by these devices have posed significant challenges for intrusion detection systems (IDS) in fog computing environments. However, conventional IDS failed to provide better attack detection performance in fog computing networks. So, this work proposes a custom convolutional neural network (CCNN) with optimal feature selection-based combat model for secured fog computing environment. Initially, preprocessing of the dataset aims to enhance the quality of the input data by removing attack labels, reducing dimensionality, and extracting relevant features. Then, comprehensive learning particle swarm-based effective seeker optimization (CLPS-ESO) is employed to extract features by leveraging a comprehensive learning strategy and the powerful optimization capabilities of effective seeker particle swarm optimization. To further enhance the feature selection performance, the random forest-dependent African buffalo optimization with weighted genetic algorithm, here after referred as RF-IABO-WGA, is utilized to identify the most discriminative features from the CLPS-ESO dataset. By selecting a subset of informative features, the computational complexity is reduced, and the detection accuracy is improved. Finally, the selected features are fed into a custom convolutional neural network (CCNN) classifier, which leverages the power of deep learning to accurately classify network traffic as either normal or malicious. The CCNN architecture can effectively learn complex patterns and capture the underlying characteristics of network data, enabling accurate intrusion detection in fog computing environments. Experimental results on a UNSW-NB dataset demonstrate that the proposed FogNet resulted in accuracy of 99.771878 %, precision of 99.770460 %, recall of 99.538589 %, and F1-score of 99.653512 %, which are superior performances compared to existing approaches.