A Comparative Analysis of Genetic Algorithm and Particle Swarm Optimization for Intrusion Detection

Abstract

This study presents a comparative analysis of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) classifiers designed for detecting wormhole attacks in Mobile Ad Hoc Networks (MANETs). These networks, characterized by their dynamic and infrastructure-less nature, are highly susceptible to security threats, necessitating robust intrusion detection systems (IDS). The primary objective of this research is to evaluate and compare the effectiveness of GA and PSO classifiers in identifying and mitigating wormhole attacks in MANETs, thereby contributing to the development of more secure and efficient network systems. Both classifiers were evaluated using key metrics such as accuracy, precision, recall, and F1-score to assess their performance. The results revealed that the PSO classifier outperformed the GA classifier, achieving a training accuracy of 80.48%, a testing accuracy of 81.02%, and an F1-score of 81.96%. In comparison, the GA classifier recorded a training accuracy of 80.02%, a testing accuracy of 80.65%, and an F1-score of 81.33%. This study underscores the potential of PSO as a more reliable tool for intrusion detection in MANETs while also identifying areas for improving the GA classifier. Future work will focus on hybrid approaches, real-world testing, and resource-efficient enhancements to optimize intrusion detection systems for secure and energy-efficient MANET environments