Hybrid Meta-Heuristic based Feature Selection Mechanism for Cyber-Attack Detection in IoT-enabled Networks

Today's technologically advanced connected world is mostly reliant on the Internet of Things (IoT)-enabled smart gadgets and easy connectivity. These smart gadgets are more susceptible to malicious practices found in network traffic, which is one of the biggest challenges in cyber security domain. As a result, many systems and end-users are adversely affected by this practice. However, intrusion detection systems (IDS) are often applied to guard against cyber-attacks. Since, IDS plays a key role in detecting and preventing cyber-attacks in IoT-enabled networks, but design of an efficient and fast IDS system for cyber-attack detection is still a challenging research issue. Moreover, IDS datasets contain multiple features and to design an efficient and fast IDS, feature selection (FS) is an essential mechanism to remove the irrelevant and redundant features from large IDS datasets. Thus, this paper has proposed a hybrid feature selection scheme in which statistical test-based filter approaches such as Chi-Square (χ^2), Pearson's Correlation Coefficient (PCC), and Mutual Information (MI) are combined with a Non-Dominated Sorting Genetic Algorithm (NSGA-II)-based metaheuristic approach for optimization of features. In the proposed scheme, filter-based methods are employed to rank the features for guided population initialization in NSGA-II for faster convergence towards a solution. Performance evaluation of the proposed scheme is evaluated using the ToN-IoT dataset in terms of number of selected features and accuracy. Experimental outcomes are compared with some latest state-of-art techniques. Result analysis confirms the superior performance of the proposed scheme with minimum number of optimized features (only 13 out of 43 features) and maximum accuracy (99.48%).