Visible to the public Using Machine Learning to Detect DoS Attacks in Wireless Sensor Networks

TitleUsing Machine Learning to Detect DoS Attacks in Wireless Sensor Networks
Publication TypeConference Paper
Year of Publication2019
AuthorsAl-issa, Abdulaziz I., Al-Akhras, Mousa, ALsahli, Mohammed S., Alawairdhi, Mohammed
Conference Name2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT)
ISBN Number978-1-5386-7942-5
Keywordsattack signature, computer network security, Decision trees, decision trees technique, denial of service, denial-of-service attack, DoS attacks, hardware resources, intrusion detection system, intrusion detection-and-prevention system, learning (artificial intelligence), machine learning techniques, Measurement, Metrics, privacy, pubcrawl, Routing protocols, security, security threats, Support vector machines, threat vectors, Wireless sensor networks, WSN
Abstract

Widespread use of Wireless Sensor Networks (WSNs) introduced many security threats due to the nature of such networks, particularly limited hardware resources and infrastructure less nature. Denial of Service attack is one of the most common types of attacks that face such type of networks. Building an Intrusion Detection and Prevention System to mitigate the effect of Denial of Service attack is not an easy task. This paper proposes the use of two machine learning techniques, namely decision trees and Support Vector Machines, to detect attack signature on a specialized dataset. The used dataset contains regular profiles and several Denial of Service attack scenarios in WSNs. The experimental results show that decision trees technique achieved better (higher) true positive rate and better (lower) false positive rate than Support Vector Machines, 99.86% vs 99.62%, and 0.05% vs. 0.09%, respectively.

URLhttps://ieeexplore.ieee.org/document/8717400
DOI10.1109/JEEIT.2019.8717400
Citation Keyal-issa_using_2019