Network traffic analysis for threats detection in the Internet of Things

Hammoudeh, M; Pimlott, J; Belguith, S; Epiphaniou, G; Baker, T; Kayes, ASM; Adebisi, B; Bounceur, A

Abstract

As the prevalence of the Internet of Things (IoT)
continues to increase, cyber criminals are quick to exploit the
security gaps that many devices are inherently designed with.
Whilst users can not be expected to tackle this threat alone, many
current solutions available for network monitoring are simply not
accessible or can be difficult to implement for the average user
and is a gap that needs to be addressed. This paper presents an
effective signature-based solution to monitor, analyse and detect
potentially malicious traffic for IoT ecosystems in the typical
home network environment by utilising passive network sniffing
techniques and a cloud-application to monitor anomalous activity.
The proposed solution focuses on two attack and propagation
vectors leveraged by the infamous Mirai botnet, namely DNS
and Telnet. Experimental evaluation demonstrates the proposed
solution can detect 98.35% of malicious DNS traffic and 99.33%
of Telnet traffic respectively; for an overall detection accuracy
of 98.84%.

• Journal Article Type: Article
• Acceptance Date: Mar 20, 2020
• Publication Date: Dec 1, 2020
• Deposit Date: Apr 20, 2020
• Publicly Available Date: Feb 1, 2021
• Journal: IEEE Internet of Things Magazine
• Print ISSN: 2576-3180
• Electronic ISSN: 2576-3199
• Publisher: Institute of Electrical and Electronics Engineers
• Volume: 3
• Issue: 4
• Pages: 40-45
• DOI: https://doi.org/10.1109/IOTM.0001.2000015
• Publisher URL: https://doi.org/10.1109/IOTM.0001.2000015
• Related Public URLs: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=8548628
• Additional Information: Access Information : © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.