Nature-inspired intrusion detection system for protecting software-defined networks controller

Abstract

Software Defined Networks (SDN) is a new emerging networking architecture facilitated by a separate controller. It has a centralized architecture that serves network management and demand fulfillment from a single point. Architecturally, SDN provides lofty benefits, but security measures are a severe concern that prevents universal adoption. If the SDN controller gets compromised, the intruders could ensign the route of network traffic based on their requirements which causes damage to the entire network. These security limitations of SDN get rectified by employing the network intrusion detection system (NIDS). Deploying ML techniques for NIDS helps us to detect the anomalies within SDN. Selecting a minimal number of features is important as it decreases the computation overhead and accelerates the NIDS performances. For feature selection, a combination of k optimal features is selected using the hit-and-trial approach. As a result, it influences the system's durability for intrusion detection and pushes the model toward poor performance. In this study, we present a new hybrid framework for feature selection using Whale Optimisation Algorithm (WOA), Fisher Score (FS), and Information gain (IG), named Whale Optimization Algorithm-Fisher Feature Importance (WOA-F2I). WOA-F2I addresses the challenge of selecting the k number of an optimal subset of features. The evaluation result manifests the WOA-F2I feature selection technique that enhances the performance of the NIDS model, which backs the input for various classifiers- support vector machine, Naive Bayes, logistic regression, and stochastic gradient descent. The proposed feature selection technique also provides better performance for binary class and multi-class attack detection.