You are here: Home Contents V14 N1 V14N1_Duffany.html
Personal tools

A Machine-Learning based Wireless Intrusion Detection System



Full text

Journal of Information System Security
Volume 14, Number 1 (2018)
Pages 2130
ISSN 1551-0123
Jeffrey L. Duffany — 1Universidad del Turabo, Puerto Rico
Carlos Y. Velez — Politechnic University, Puerto Rico
Information Institute Publishing, Washington DC, USA




One method of designing an Intrusion Detection System (IDS) is to have it first learn what is normal behaviour, and then program it to send an alert whenever a significant deviation occurs. A Software Defined Radio (SDR) system can scan a desired range of the radio frequency spectrum and obtain periodic snapshots of communication activity, for example WiFi spectra. Machine learning techniques can then be applied to detect anomalous activity over the airwaves. Cluster analysis demonstrated the possibility of developing an IDS using a wavelet transform to convert WiFi spectra into a feature vector comprised of the energy in each wavelet component. Training sets of 100 WiFi spectra were used, some with intrusions and others not. The R Language was used to implement the prototype IDS using both the Naive Bayes and Neural Networks classifiers.




Intrusion Detection System, Wavelet, Machine Learning, Cluster Analysis, Software Defined Radio WiFi




Akansu, A. N., Serdijn, W. A. and Selesnick, I. W., 2009. Emerging applications of wavelets: A review. Physical Communication. 3: 1. doi:10.1016/j.phycom.2009.07.001.

Amin H. U., Malik A.S., Ahmad R.F., Badruddin N., Kamel N., Hussain M., and Chooi W.T., 2015. Feature Extraction and Classification for EEG signals using Wavelet Transform and Machine Learning Techniques, Australas Phys Eng Sci Med. 2015 Mar;38(1):139-49. doi: 10.1007/s13246-015-0333-x.

Dillinger, M., Madani, K. and Alonistioti, N., 2003. Software Defined Radio: Architectures, Systems and Functions, Wiley & Sons, 2003. ISBN 0-470-85164-3.

Karpagachelvi, S., Arthanari, M., and Sivakumar, M., 2011. Classification of Electrocardiogram Signals with Extreme Learning Machine and Relevance Vector Machine, International Journal of Computer Science Issues, Vol. 8, Issue 1, January 2011.

Lantz, B., 2015. Machine Learning with R, Second Edition, Packt Publishing, July 31, 2015. ISBN-13: 978-1784393908.

Scarfone, K. and Mell, P., 2010. Guide to Intrusion Detection and Prevention Systems (IDPS), Computer Security Resource Center, National Institute of Standards and Technology, 800-94, January 2010.