Support Vector Machine Based DDoS Detection and Mitigation in Software Defined Networks
DOI:
https://doi.org/10.56536/jicet.v4i2.161Abstract
The Software Defined Networking (SDN) is an innovative network architecture that offers flexible and programable networks through a centralized controller. However, If the controller fails the whole system becomes paralyzed. The Distributed Denial of Service (DDoS) attack is one of the main threats to the SDN controller, as it exhausts the resources of the SDN controller which disturbs the whole network and affects the performance of the network. In this regard, we propose a Support Vector Machine (SVM) based machine learning classifier to detect the DDoS attacks on SDN controller. Once the attack is detected by the classifier, mitigation module is invoked to block the attack flows. The objective is to detect DDoS attacks with high accuracy and mitigate them in a short period of time. We evaluate our proposed solutions on two different publicly available datasets. i.e., KDD and KDD’99