Towards an efficient anomaly‐based intrusion detection for software‐defined networks. Issue 6 (1st November 2018)

• Record Type: Journal Article
• Authors: Latah, Majd; Toker, Levent
• Is Part Of: IET networks. Volume 7:Issue 6(2018)
• Page Start: 453
• Page End: 459
• Publication Date: 2018-11-01
• Subjects: security of data -- learning (artificial intelligence) -- support vector machines -- decision trees -- software defined networking -- Bayes methods -- neural nets; software‐defined networks -- flexible network applications -- SDN controller -- centralised controlling point -- secure network -- supervised machine‐learning approaches -- neural networks -- anomaly‐based intrusion detection system -- receiver operator characteristic curve -- McNemar test -- decision trees -- extreme learning machine -- Naive Bayes -- linear discriminant analysis -- support vector machines -- random forest -- K‐nearest‐neighbour -- AdaBoost -- RUSBoost -- LogitBoost -- BaggingTrees -- NSL‐KDD benchmark dataset; Computer network architectures -- Periodicals; Computer network protocols -- Periodicals; Information networks -- Periodicals; Telecommunication systems -- Periodicals; 004.605
• DOI: 10.1049/iet-net.2018.5080
• Languages: English
• ISSNs: 2047-4954

Abstract

Abstract : Software‐defined networking (SDN) is a new paradigm that allows developing more flexible network applications. A SDN controller, which represents a centralised controlling point, is responsible for running various network applications as well as maintaining different network services and functionalities. Choosing an efficient intrusion detection system helps in reducing the overhead of the running controller and creates a more secure network. In this study, we investigate the performance of the well‐known anomaly‐based intrusion detection approaches in terms of accuracy, false alarm rate, precision, recall, f1‐measure, area under receiver operator characteristic curve, execution time and McNemar's test. Precisely, the authors focus on supervised machine‐learning approaches where we use the following classifiers: decision trees, extreme learning machine, Naive Bayes, linear discriminant analysis, neural networks, support vector machines, random forest, K‐nearest‐neighbour, AdaBoost, RUSBoost, LogitBoost and BaggingTrees where we employ the well‐known NSL‐KDD benchmark dataset to compare the performance of each one of these classifiers.