9417cnc04.pdf - International Journal of Computer Networks...

This preview shows page 1 - 3 out of 12 pages.

International Journal of Computer Networks & Communications (IJCNC) Vol.9, No.4, July 2017 DOI: 10.5121/ijcnc.2017.9404 45 I NVESTIGATION OF C OMPUTATIONAL I NTELLIGENCE T ECHNIQUES FOR I NTRUSION D ETECTION IN W IRELESS S ENSOR N ETWORKS Christopher D. McDermott and Andrei Petrovski School of Computing Science and Digital Media, Robert Gordon University, Aberdeen, Scotland A BSTRACT Wireless Sensor Networks (WSNs) have become a key technology for the IoT and despite obvious benefits, challenges still exist regarding security. As more devices are connected to the internet, new cyber attacks are emerging which join well-known attacks posing significant threats to the confidentiality, integrity and availability of data in WSNs. In this work, we investigated two computational intelligence techniques for WSN intrusion detection. A back propagation neural network was compared with a support vector machine classifier. Using the NSL-KDD dataset, detection rates achieved by the two techniques for six cyber attacks were recorded. The results showed that both techniques offer a high true positive rate and a low false positive rate, making both of them good options for intrusion detection. In addition, we further show the support vector machine classifiers suitability for anomaly detection, by demonstrating its ability to handle low sample sizes, while maintaining an acceptable FPR rate under the required threshold. K EYWORDS Wireless Sensor Networks (WSNs), Intrusion Detection System (IDS), Denial of Service (DoS), Artificial Neural Network (ANN), Feed-forward Backpropagation, Support Vector Machine (SVM). 1. I NTRODUCTION The Internet of Things (IoT) is expected to usher in an era of increased connectivity, with an estimated 50 billion devices expected to be connected to the Internet by 2020 [1]. At its core, the aim of the IoT is to connect previously unconnected devices to the Internet [2], thus creating smart devices capable of collecting, storing and sharing data, without human interaction [3]. These newly connected smart devices join previously connected traditional computing devices, to form a hybrid network known as the IoT. With the rapid growth of the IoT, and the technological development of sensors, Wireless Sensor Networks (WSNs) have become a key technology for the IoT [4]. These networks consist of self- organized sensor nodes, communicating using a wireless medium and are used to perform distributed sensing tasks. The low cost nature and easy implementation has seen them deployed in a wide range of fields such as surveillance, climate change detection, environment monitoring, and numerous healthcare applications [5]. Despite the obvious benefits, challenges still exist with respect to security in WSNs. This is largely due to the inherent nature of being deployed in harsh unattended environments, broadcast in nature, and having limited resources [6] [7]. To address these concerns, extensive research has been conducted into the use of cryptography, authentication, key management and secure routing in WSNs. Whilst the proposed security solutions have been found to reduce cyber attacks, they
Image of page 1

Subscribe to view the full document.

International Journal of Computer Networks & Communications (IJCNC) Vol.9, No.4, July 2017
Image of page 2
Image of page 3

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern