Enhancing the Efficiency of DDoS Attack Detection in IoT Networks Using Machine Learning

Abstract

Modern connectivity has been revolutionized by the Internet of Things (IoT). The limited computational capabilities of IoT devices make them vulnerable to various attacks including, Distributed Denial of Service (DDoS) attacks that compromise the availability of these devices and their services. This research introduces a machine learning-based approach to enhance DDoS attack detection in IoT environments. Using the CICIoT2023 dataset, we evaluated several machine learning models: Random Forest, XGBoost, Decision Tree, and K-Nearest Neighbors. The results demonstrated high classification performance across all models. XGBoost achieved the highest accuracy of 99.97% with a prediction time of 0.4735 seconds, while Decision Tree delivered the best prediction time of 0.1879 seconds, maintaining a high accuracy of 99.94%.

The results of the article confirm that the suggested machine learning models for DDoS attack detection in IoT networks are effective and improve the security of such networks.