A machine learning-based lightweight intrusion detection system for the internet of things

被引：31
作者：
Fenanir S. [1 ]
Semchedine F. [2 ]
Baadache A. [3 ]
机构：
[1] Department of Computer Science, Faculty of Exact Sciences, University of Bejaia, Bejaia
[2] Institute of Optics and Precision Mechanics (IOMP), University of Setif 1, Setif
[3] University of Alger 3, Algiers
来源：
Revue d'Intelligence Artificielle | 2019年 / 33卷 / 03期
关键词：
Anomaly detection; Feature selection; Internet of things (IoT); Intrusion detection system (IDS);
D O I：
10.18280/ria.330306
中图分类号：
学科分类号：
摘要：
The Internet of Things (IoT) is vulnerable to various attacks, due to the presence of tiny computing devices. To enhance the security of the IoT, this paper builds a lightweight intrusion detection system (IDS) based on two machine learning techniques, namely, feature selection and feature classification. The feature selection was realized by the filter-based method, thanks to its relatively low computing cost. The feature classification algorithm for our system was identified through comparison between logistic regression (LR), naive Bayes (NB), decision tree (DT), random forest (RF), k-nearest neighbor (KNN), support vector machine (SVM) and multilayer perceptron (MLP). Finally, the DT algorithm was selected for our system, owing to its outstanding performance on several datasets. The research results provide a guide on choosing the optimal feature selection method for machine learning. © 2019 Lavoisier. All rights reserved.
引用
收藏
页码：203 / 211
页数：8
相关论文
共 25 条
  • [1] Atzori L., Iera A., Morabito G., The internet of things: A survey, Computer Network, 54, 15, pp. 2787-2805, (2010)
  • [2] Weiser M., The computer for the 21st century, Scientific American, 265, 3, pp. 94-105, (1991)
  • [3] Sedjelmaci H., Senouci S.M., Al-Bahri M., Lightweight anomaly detection technique for low-resource IoT devices: A game-theoretic methodology, IEEE ICC - Mobile and Wireless Networking Symposium, (2016)
  • [4] Raza S., Wallgren L., Voigt T., SVELTE: Real-time intrusion detection in the internet of things, Ad Hoc Networks, 11, 8, pp. 2661-2674, (2013)
  • [5] Anand A., Patel B., An overview on intrusiondetection system and types of attacks it can detectconsidering different protocols, International Journal of Advanced Research in Computer Science and Software Engineering, 2, 8, pp. 94-98, (2012)
  • [6] Rajasegarar S., Leckie C., Palaniswami M., Anomaly detection in wireless sensor networks, IEEEWireless Communications, 15, 4, pp. 34-40, (2008)
  • [7] Li W.C., Yi P., Wu Y., Pan L., Li J.H., A newintrusion detection system based on KNN classificationalgorithm in wireless sensor network, Journal of Electrical and Computer Engineering, 2014, (2014)
  • [8] Thanigaivelan N.K., Nigussie E., Kanth R.K., Virtanen S., Isoaho J., Distributed internal anomalydetection system for internet-of-things, 13th IEEEAnnual Consumer Communications & Networking Conference (CCNC), (2016)
  • [9] Summerville D.H., Zach K.M., Chen Y., Ultra-lightweight deep packet anomaly detection for internet of things devices, 2015 IEEE 34th International Performance Computing and Communications Conference (IPCCC), (2015)
  • [10] Huang S.H., Dimensionality reduction inautomatic knowledge acquisition: A simple greedysearch approach, IEEE Transactions on Knowledge and Data Engineering, 15, 6, pp. 1364-1373, (2003)
123