Manjula, C B and Muniyal, Balachandra (2020) Multiple intrusion detection in RPL based networks. International Journal of Electrical and Computer Engineering, 10 (1). pp. 467-476. ISSN 2088-8708

PDF 8340.pdf - Published Version Restricted to Registered users only Download (602kB) | Request a copy

Abstract

Routing Protocol for Low Power and Lossy Networks based networks consists of large number of tiny sensor nodes with limited resources. These nodes are directly connected to the Internet through the border router. Hence these nodes are susceptible to different types of attacks. The possible attacks are rank attack, selective forwarding, worm hole and Denial of service attack. These attacks can be effectively identified by intrusion detection system model. The paper focuses on identification of multiple intrusions by considering the network size as 10, 40 and 100 nodes and adding 10%, 20% and 30% of malicious nodes to the considered network. Experiments are simulated using Cooja simulator on Contiki operating system. Behavior of the network is observed based on the percentage of inconsistency achieved, energy consumption, accuracy and false positive rate. Experimental results show that multiple intrusions can be detected effectively by machine learning techniques.

Item Type:	Article
Uncontrolled Keywords:	Intrusion detection Machine learning Network security RPL / 6LoWPAN networks Wireless sensor networks
Subjects:	Engineering > MIT Manipal > Information and Communication Technology
Depositing User:	MIT Library
Date Deposited:	07 May 2020 06:21
Last Modified:	07 May 2020 06:21
URI:	http://eprints.manipal.edu/id/eprint/155101

Actions (login required)

View Item