Network Intrusion Detection in MANET Using Improved Whale Optimization Algorithm-SVM

Abstract

Presently, the MANET is indispensable for network administration because of the collaborative efforts of its individual nodes. Due to the dynamic nature of the network's nodes, this type of node might emerge for many different causes. In a MANET, you could be vulnerable to DDoS attacks, probing assaults, R2L attacks, and U2R attacks, to name a few. These kinds of threats are detrimental to the MANET. Consequently, a large toolkit of techniques is used to detect attacks and wipe them out of MANET. It is important to limit the possibility of attacks, and optimization is a major factor in doing so. This paper presents a new approach for intrusion detection using the Improved Whale Optimization Algorithm (IWOA) to select the most relevant features from the NSL-KDD dataset. The selected features are then used to train a Support Vector Machine (SVM) classifier for improved intrusion detection performance. Experimental results on the NSL-KDD dataset show that the proposed approach outperforms existing methods in terms of accuracy and efficiency.