Analysis of Features Dataset for DDoS Detection by using ASVM Method on Software Defined Networking

Abstract

The impact of Distributed Denial of Service (DDoS) attack is one of the major concerns for Software Defined Networking (SDN) environments. Support Vector Machine (SVM) has been used in a DDoS attack detection mechanism on SDN. The advantages of SVM algorithms in DDoS attack detections are high accuracy and low false positive rate. However, SVM algorithm takes too long for training and testing time. A large number of literatures have been tried to get better results in a SVM-based DDoS attack detection. They proposed various kinds of SVM-based detection methods. Their results were measuring and evaluating by using various evaluation metrics. As a result, a SVM-based detection performance depends on the nature of traffic datasets. In this paper, our focus is to analyze the extracted features from the SDN traffics dataset resulting on a reduction of bias data from the dataset. SDN traffics features dataset were validated by using 10-fold cross-validation method. The effectiveness of our created dataset was validated by comparing with other dataset, e.g. KDDCUP 99 dataset. In conclusion, our proposed dataset can be used effectively for SVM on SDN.

Keywords

• cross-validation
• distributed denial of service
• performance evaluation
• software defined networking
• support vector machine