ANALYTICAL STUDY OF APSO-DT HYBRID MODEL FOR INTELLIGENT INTRUSION DETECTION

Abstract

Intrusion detection system (IDS) plays a vital role in ensuring network security by identifying unauthorized access and malicious activity. Traditional IDS approaches often suffer from high false alarm rates and limited detection capabilities. This analytical study introduces a novel hybrid framework that integrates Adaptive Particle Swarm Optimization (APSO) with Decision Tree (DT) classification to intelligently enhance intrusion detection performance. The APSO algorithm is employed to optimize feature selection, while the refined DT model improves classification accuracy, forming a robust and adaptive detection mechanism. The proposed APSO-DT hybrid model is validated using the NSL-KDD dataset, a standard benchmark in cybersecurity research. Experimental evaluations reveal that the hybrid approach achieves superior detection rates, improved accuracy, and reduced false alarms compared to conventional methods. This work contributes to the field of applied mathematics and computer science by providing an intelligent optimization-based approach to critical real-world problems in cybersecurity.