A novel Machine Learning-based Network Intrusion Detection System for Software-Defined Network

Network Intrusion Detection System (NIDS) is an important component in many network systems. The rapid development of the Internet requires NIDS to improve performance in terms of both accuracy and efficiency. In this paper, we propose a flow-based anomaly detection system in applying Machine Learning approach in a SDN network. The paper implements a testbed to achieve an eight-feature dataset as the input for training six Machine Learning models. The obtained experimental results showed that the proposed NIDS is potentially a good security solution for a SDN network.