An Anomaly-Based Method for DDoS Attacks Detection using RBF Neural Networks
Reyhaneh Karimazad, Ahmad Faraahi · 2011
Distributed denial of service (DDoS) attacks are serious threats for availability of the internet services. These types of attacks command multiple agents to send a great number of packets to a victim and thus can easily exhaust the resources of the victim. In this paper we propose an anomaly-based DDoS detection method based on the various features of attack packets, obtained from study the incoming network traffic and using of Radial Basis Function (RBF) neural networks to analyze these features. We evaluate the proposed method using our simulated network and UCLA Dataset. The results show that the proposed system can make real-time detection accuracy better than 96% for DDoS attacks.