SVM Approach with CTNT to Detect DDoS Attacks in Grid Computing

摘要

In the last several years, DDoS attack methods become more sophisticated and effective. Hence, it is more difficult to detect the DDoS attack. In order to cope with these problems, there have been many researches on DDoS detection mechanism. However, the common shortcoming of the previous detection mechanisms is that they cannot detect new attacks. In this paper, we propose a new DDoS detection model based on Support Vector Machine (SVM). The proposed model uses SVM to automatically detect new DDoS attacks and uses Concentration Tendency of Network Traffic (CTNT) to analyze the characteristics of network traffic for DDoS attacks. Experimental results show that the proposed model can be a highly useful to detect various DDoS attacks.