Intrusion Detection of Distributed Denial of Service Attack in Internet of Things Network Using Adaboost and Support Vector Machine

Abstract

Distributed denial-of-service (DDoS) attacks pose a significant threat to computer networks and systems by disrupting services through the saturation of targeted systems with traffic from multiple sources. Real-time detection of these attacks has become a critical cyber security task. However, current DDoS attack detection methods suffer from high false positive rates and limited ability to capture the complex patterns of attack traffic. This research developed an effective non-real-time DDoS attack detection system for IoT networks. The methods chosen for this research, including Support Vector Machines (SVM), Adaptive Boosting (AdaBoost), and feature selection techniques i.e Mutual Information (MI) and Recursive Feature Elimination with Cross-Validation (RFECV) on CICIDS2019 dataset. The SVM-AdaBoost classifier achieved an accuracy of approximately 99.9% the precision is 99.5% Recall 99.1%, F1score 99.3% and AUC-ROC 100%. While the training time display an average time of 1.2031sec. The results of this study suggest that security professionals and researchers should consider adopting ensemble methods like AdaBoost, especially when combined with robust base learners such as SVM, in the development of intrusion detection systems for IoT networks