Statistical Anomaly Detection of DDoS Attacks Using K-Nearest Neighbour
Thwe Thwe Oo, Thandar Phyu · 2014
Distributed Denial of Service (DDoS) attacks have strong influence on Internet Security because these attacks affect the normal functioning of organizations causing billions of dollars of losses. Although these organizations were well-equipped in security, they were damaged by DDoS attacks. In this paper, the proposed system presents both detecting and classifying sheme of DDoS attack using K-NN. The two proposed algorithms are developed based on various features of attack packets obtained from study the incoming and outgoing network traffic and used K-Nearest Neighbour to analyze these features. The main objectives of this paper are to analyze the DDoS attacks natures and to detect and identify types of DDoS attacks.