NORMA eResearch @NCI Library

Intrusion Detection in IoT Systems using Machine Learning

Arhore, Samuel Avwerosughene (2022) Intrusion Detection in IoT Systems using Machine Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (3MB) | Preview


Data and device security has become increasingly important as the Internet of Things (IoT) develops and is used globally. In IoT, there are an enormous number of devices and they are all configured differently, making it difficult to develop trusted interconnections between many of these nodes. Intrusion Detection Systems (IDS) that work collaboratively often deliver better intrusion detection performance, since nodes in an IDS can exchange information between each other to ensure effective intrusion detection. Due to their power consumption, loT devices are normally unable to perform a number of computations. Therefore, encryption and authentication do not provide effective protection from malicious cyber-attacks. Since intrusions pose a threat to security, IDSs have become the forefront of security solutions, detecting abnormal and malicious activities in IoT networks using machine learning algorithms has shown promising results recently. An analysis of several machine learning techniques is presented in the paper in order to determine which one performs best with a chosen set of datasets in detecting intrusion. Each of them is also discussed in terms of its limitations. Using a set of four performance metrics; recall, precision, classification accuracy and F1 score, a confusion matrix is created and the system's performance will be evaluated following an experiment applied with an up-to-date and relevant dataset. It is expected that by the end of this study, a suitable algorithm will be proposed which detects network intrusions in a minimal amount of time with accurate results. The winner technique achieved 99% accuracy to a high degree of efficiency and accuracy in a short amount of time.

Item Type: Thesis (Masters)
Ayala-Rivera, Vanessa
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
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Cyber Security
Depositing User: Tamara Malone
Date Deposited: 24 Apr 2023 14:20
Last Modified: 24 Apr 2023 14:20

Actions (login required)

View Item View Item