Detection of (D)DOS attacks based on online change point analysis

SIP (Session Initiation Protocol) is one of the most common protocols that enables session control in today's communication networks. The SIP networks are also targeted by the malicious users. This study focuses on adaptive intelligent systems that detect the changes on the network flow using anomaly detection methods. Two different change point models that are based on distance and sparse signal representation are proposed. The accuracy of the proposed systems are compared over simulation data collected.