Detection of security threats in SDN paradigm using Machine Learning Algorithms

Abstract

With emerging 5G, big data applications, loT technology the demand of performance improvement in currently used traditional network have made researchers to think of an entirely new network architecture that is SDN (Software Defined Networking). Although it is in developing stage, it is already evident that this architecture is not free from prevalent security threats. Moreover, these security threats can have more damaging impact on SDN network than traditional network due to some critical vulnerabilities existing in the architecture. Researchers have found several methods of detecting those security threats. One of them is the application of machine learning algorithms. Our work focuses on the application of these machine learning algorithms - (i) Multiple Layer Perceptron (MLP), (ii) Support Vector Machine (SVM), (iii) Decision Tree and (iv) Random Forest algorithm and analyze, compare their performance.