ADVANCED DDOS DETECTION IN IOT NETWORKS USING ENSEMBLE MACHINE LEARNING TECHNIQUES

Abstract

The rapid growth of Internet of Things (IoT) devices has significantly increased the attack surface for cyber threats, particularly Distributed Denial of Service (DDoS) attacks. These attacks disrupt network services by overwhelming systems with malicious traffic. Traditional intrusion detection systems and basic machine learning techniques fail to provide accurate and real-time detection due to the high volume and dynamic nature of IoT traffic. This paper proposes an advanced DDoS detection system using ensemble machine learning techniques. The proposed framework combines Random Forest, XGBoost, and K-Nearest Neighbors (KNN) algorithms to improve detection accuracy and efficiency. The model preprocesses IoT network traffic data, extracts important features, and performs real-time monitoring to identify malicious activities. Experimental analysis shows that the ensemble learning approach achieves higher accuracy, faster response time, and improved scalability compared to traditional detection systems. The proposed system effectively detects multiple DDoS attack types and provides real-time alerts and mitigation support for secure IoT environments.