Artificial Neural Network (ANN) Based DDoS Attack Detection Model on Software Defined Networking (SDN)

Abstract

Software Defined Networking (SDN) is a modern emerging technology in networking. The great advantage of this network is, decoupling of the carrier plane and the control plane as well as which provides centralized control. A Controller is the intelligent part of SDN. It offers several benefits such as network programmability, dynamic computing, and cost-effective, high bandwidth. However, SDN has many security issues. The DDoS attack on SDN is a significant issue, and various proposals have been proposed for the detection and prevention of attacks. The main objective of this proposal is to detect DDoS attacks with the help of SDN techniques. In this proposal, a deep learning based Artificial Neural Network (ANN) model is used to detect the DDoS attacks. This can reduce learning time as well as detection time. To evaluate our model we use different machine learning algorithms and deep learning algorithm with different optimizers to train the network traffic which is generated in Mininet emulator and evaluates the results by various metrics such as detection rate, accuracy score, and confusion matrix with classification report. The result shows less detection time (4Secs)with a high accuracy score of 92% in our proposed Artificial Neural Network (ANN) model.

Software Defined Networking Based Detection of DDoS Attacks

“…DDoS attack identification makes heavy use of machine learning methods like artificial neural networks (ANN) [9], support vector machines (SVM), and others. Various methods such as support vector machines [10], fuzzy reasoning [11], decision trees [12], genetic algorithms [13], naive bayes [4], and k-means [14] are used for cluster analysis. Attacks on Software-Defined Networks via Distributed Denial of Service can be detected and prevented using the methods detailed in Table I.…”