Analyses of flow based techniques to detect Distributed Denial of Service attacks

Distributed Denial of Service (DDoS) attacks comprise of sending huge network traffic to a victim system using multiple systems. Detecting such attacks has gained much attention in current literature. Studies have shown that flow-based anomaly detection mechanisms give promising results as compared to typical signature based attack detection mechanisms which have not been able to detect such attacks effectively. For this purpose, a variety of flow-based DDoS detection algorithms have been put forward. We have divided the flow-based DDoS attack detection techniques broadly into two categories namely, packet header based and mathematical formulation based. Analyses has been done for two techniques one belonging to each category. The paper has analyzed and evaluated these with respect to their detection accuracy and capability. Finally, we have suggested improvements that can be helpful to give results better than both the previously proposed algorithms. Furthermore, our findings can be applied to DDoS detection systems for refining their detection capability.