Software-Defined Networking (SDN) is a novel networking paradigm that enhanced programming abilities, which can be used to solve traditional challenges on the basis of more efficient approaches. The most element in the SDN paradigm is the controller, which is responsible managing the flows of each correspondence forwarding element (switch or). Flow statistics provided by the controller are considered to be useful that can be used to develop a network-based intrusion detection. Therefore, in this paper, we propose a 5-level hybrid classification based on flow statistics in order to attain an improvement in the accuracy of the system. For the first level, we employ the k-Nearest approach (kNN); for the second level, we use the Extreme Learning (ELM); and for the remaining levels, we utilize the Hierarchical Learning Machine (H-ELM) approach. In comparison with conventional machine learning algorithms based on the NSL-KDD benchmark dataset, experimental study showed that our system achieves the highest level of (84.29%). Therefore, our approach presents an efficient approach for detection in SDNs.
No takes yet. Share an insight, caveat, or question.
Latah et al. (2018) studied this question.