Software-defined networking (SDN) is a promising approach to networking that provides an abstraction layer for the physical\nnetwork. This technology has the potential to decrease the networking costs and complexity within huge data centers. Although\nSDN offers flexibility, it has design flaws with regard to network security. To support the ongoing use of SDN, these flaws must be\nfixed using an integrated approach to improve overall network security. Therefore, in this paper, we propose a recurrent neural\nnetwork (RNN) model based on a new regularization technique (RNN-SDR). This technique supports intrusion detection within\nSDNs. The purpose of regularization is to generalize the machine learning model enough for it to be performed optimally.\nExperiments on the KDD Cup 1999, NSL-KDD, and UNSW-NB15 datasets achieved accuracies of 99.5%, 97.39%, and 99.9%,\nrespectively. The proposed RNN-SDR employs a minimum number of features when compared with other models. In addition,\nthe experiments also validated that the RNN-SDR model does not significantly affect network performance in comparison with\nother options. Based on the analysis of the results of our experiments, we conclude that the RNN-SDR model is a promising\napproach for intrusion detection in SDN environments.
Loading....