Authors V.I. Vasilyev, I.V. Sharabyrov
Month, Year 02, 2014 @en
Index UDC 681.5:004(07)
Abstract Nowadays wireless networks, including local ones, continue to evolve rapidly. Herewith security in these networks does not often correspond to the required level. One of the most actual protection means from the wireless attacks are the intrusion detection systems. Due to the extensive spread and wide possibilities of modern data mining methods, the task of network traffic parameters analysis for the signs of attack can be solved by application of these methods. The article provides an overview of network attacks that are relevant to local wireless networks, as well as a comparison of data mining techniques, which can be used to detect the types of attacks mentioned above. The data mining techniques considered are support vector machine, k-nearest neighbor method, neural networks and decision trees. The experimental results allow making the conclusion about practical relevance of proposed approach for intrusion detection in local wireless networks.

Download PDF

Keywords Wireless network; network attack; detection model; signature; Wi-Fi.
References 1. Ross D. Securing IEEE802.11 Wireless LANs. PhD thesis, Queensland University of Technology, 2010 [Электронный ресурс]. URL: 37638/1/David_Ross_ Thesis.pdf (дата обращения 28.01.2013).
2. Nguyen T., Nguyen B., Pham H. An efficient solution for preventing Dis’ing attack on 802.11 networks // The 2012 International Conference on Green Technology and Sustainable Development (GTSD2012): Journal of Engineering Technology and Education, Hochiminh City, 2012. – P. 395-403.
3. Sinclair C., Pierce L., Matzner S. An Application of Machine Learning to Network Intrusion Detection // Proceedings of Computer Security Applications Conference (ACSAC '99). – 1999. – P. 371-377.
4. Tang H., Cao Z. Machine Learning-based Intrusion Detection Algorithms // Journal of Computational Information Systems. – 2009. – P. 1825-1831.
5. Mukkamala S., Janoski G., Sung A. Intrusion Detection: Support Vector Machines and Neural Networks [Электронный ресурс]. URL: class/fa05/cs591han/ papers/mukkCNN02.pdf (дата обращения 09.01.2013).
6. Mulay S., Devale P., Garje G. Intrusion Detection System using Support Vector Machine and Decision Tree // International Journal of Computer Applications. – 2010. – Vol. 3, № 3. – P. 40-43.
7. Arinze N. Wireless Local Area Network (WLAN): Security Risk Assessment and Countermeasures. Blekinge Institute of Technology, 2008 [Электронный ресурс]. URL: http:// 1257514004fce3f/$file/WLAN_Security% 20Risk%20Assessment%20and%20Countermeasures.pdf (дата обращения 12.03.2013).
8. WVE. Wireless Vulnerabilities and Exploits [Электронный ресурс]. URL: (дата обращения 05.10.2013).
9. The NSL-KDD Data Set. [Электронный ресурс]. URL: (дата обращения 22.01.2013).
10. KDD cup 99 Intrusion detection data set. [Электронный ресурс]. URL: (дата обращения 19.11.2011).
11. Lincoln Laboratory. DARPA Intrusion Detection Evaluation. [Электронный ресурс]. URL: cyber/CSTcorpora/ ideval/docs/attackDB.html (дата обращения 01.04.2012).
12. Миронов К.В., Шарабыров И.В. О применении метода опорных векторов в системах обнаружения атак // Мавлютовские чтения: Всероссийская молодежная научная конференция: сборник трудов в 5 т. Т. 3. – УГАТУ, 2012. – С. 28-30.
13. Васильев В.И. [и др.]. Разработка модели обнаружения сигнатур атак на основе метода опорных векторов // Материалы XII Международной научно-практической конференции «Информационная безопасность-2012». Ч. 1. – Таганрог: Изд-во ТТИ ЮФУ, 2012. – С. 192-201.
14. Olusola A., Oladele A., Abosede D. Analysis of KDD ’99 Intrusion Detection Dataset for Selection of Relevance Features // Proceedings of the World Congress on Engineering and Computer Science. San Francisco, 2010. – Vol. 1. – P. 162-168.
15. RapidMiner Studio. [Электронный ресурс]. URL: (дата обращения 01.09.2013).

Comments are closed.