Evaluating the Impact of Feature Engineering Techniques on Supervised Machine Learning Algorithms for IoT Intrusion Detection Systems: A case Study on Mirai Botnet Attacks

Allam, Dina Abdelnasser (2025) Evaluating the Impact of Feature Engineering Techniques on Supervised Machine Learning Algorithms for IoT Intrusion Detection Systems: A case Study on Mirai Botnet Attacks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (3MB) | Preview

Abstract

In this new era, the integration of internet of things (IoT) devices in everyday environment became essential and demandable, this integration also broadens the global attack surface. This resulting with massive increase in IoT malware records between 2024 and 202. Long–standing attacks such as Mirai botnet continue to evolve, reinforcing the need of intrusion detection systems (IDS). This study evaluates the impact of different feature engineering techniques on the performance of supervised machine learning models in detecting Mirai botnet attacks, using recent Dataset. This study utilised most recent dataset named CIC IoT-DIAD 2024 that focusing on flow-based features of Mirai attacks. Three feature configurations were evaluated: original features, Autoencoder features and combined Autoencoder and PCA features on four supervised machine learning algorithms including Logistic regression, Random Forest, XGBoost and LightGBM. The results computed based on confusion matrix, showing that the best performance model were Random Forest and LightGBM using the original feature set with ~93% accuracy. These results highlighted the strength of ensemble machine learning models against linear models, it also showed that not always the feature engineering and reduction techniques enhance the performance. Future studies should explore more hand-crafted feature extraction techniques and deep learning models to enhance IDS detection rate.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mustafa, Raza Ul UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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:	Ciara O'Brien
Date Deposited:	03 Sep 2026 10:14
Last Modified:	03 Sep 2026 10:42
URI:	https://norma.ncirl.ie/id/eprint/9788

Actions (login required)

View Item