An Efficient Intrusion Detection System for SDN using Convolutional Neural Network

With the accelerated development of computer network utilization and the enormous growth of the number of applications running on top of networks, network security has become more significant. Intrusion Detection Systems (IDS) are considered as essential tools that can be utilized to protect computer networks and information systems. Software-Defined Network (SDN) architecture is used to provide network monitoring and observation of functions. Generally, an IDS is developed to observe the regular traffic to the SDN in order to maintain a high level of security. This paper introduces an efficient IDS using Convolutional Neural Network (CNN). This IDS is applied on a new attack-specific SDN dataset called InSDN. The proposed IDS is compared in performance with different machine-learning-based systems such as Decision Tree Classifier (CART), Logistic Regression (LR), Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF) classifier, and AdaBoost (AB) classifier.