An approach for malware detection on IoT systems using machine learning

Alves Fagundes, Jonatas (2021) An approach for malware detection on IoT systems using machine learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (783kB) | Preview
Preview	PDF (Configuration manual) Download (602kB) | Preview

Abstract

Internet of things (IoT) devices communicate, collect and exchange data about our online activities and preferences via the internet. These smart devices are infiltrated into our lives in houses, workplaces, cities and it generates millions of gigabytes data every day. However, any device that shares data through the internet is vulnerable to cyberattacks. It is known that most IoT devices are built containing poor security which makes them attractive targets to cybercriminals. Malware detection has been a research area that is constantly studied due to the evolution of malwares and its vectors. Machine learning techniques have been presented as one of the most efficient and effective solutions to identify different vectors of attacks in IoT devices. This research aims to present a study of the implementation of machine learning techniques in the detection of malware to address vulnerabilities in IoT environments. This work explores ways to identify normal and anomalous behaviours in IoT systems using machine learning algorithms as classifiers that include Random Forest, Artificial Neural Network - Multilayer Perceptron, K-nearest Neighbors, and Support Vector Machine. In this work, we could identify that Random Forest presents better results identifying malicious behaviour based on tests, previous work, and other sources.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security H Social Sciences > HV Social pathology. Social and public welfare > Criminology > Crimes and Offences > Cyber Crime
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Clara Chan
Date Deposited:	14 Oct 2021 15:28
Last Modified:	18 Oct 2021 13:58
URI:	https://norma.ncirl.ie/id/eprint/5099

Actions (login required)

View Item