Recurrent Neural Network Model Based on a New Regularization Technique for Real-Time Intrusion Detection in SDN Environments

Abstract

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

Intrusion Detection System in Software-Defined Networks Using Machine Learning and Deep Learning Techniques –A Comprehensive Survey

“…Albahar [189] presents an RNN based DL-based model on a novel regularization method called RNN-SDR by decaying the weights according to the calculated standard deviation of weight matrices and then matches the result through its predecessor. The proposed system is a 3-part framework collects flow information at stage-1.…”

“…As a result, another open issue is using multiple physical computers to evaluate suggested security measures in the SDN paradigm. The Mininet emulator was used to replicate and test the majority of the reviewed ML-DL-based IDS solutions, such as [167], [171], [189], [191], [234], [246]. On the one hand, a Mininet simulator makes prototyping an SDN easier and may be used to illustrate the concept of the proposed system.…”

“…However, we have found an apparent lack of study in all the research papers, especially IDSs that are DL based and did not mention much about the hyper-tuning parameters to train the model. Some papers [147], [152], [186], [189], [203], [221] mentioned finding the useful hyperparameters using the grid search technique. Though feature selection significantly influences IDS' performance, only a few researchers use it as the primary component of their studies.…”

A Single-Label Model to Ensure Data Consistency in Information Security

“…Software-defined networking (SDN) is a promising approach to networking which provides an abstraction layer for the physical network [28]. In published literature, a recurrent neural network (RNN) model based on a new regularization technique (RNN-SDR) was proposed by the authors.…”

“…is technique supported intrusion detection within SDNs [28]. Nevertheless, this model is not practical for implementation in the context of an SDN.…”