Date of Award

2026

Degree Name

Mathematics

College

College of Science

Type of Degree

M.S.

Document Type

Thesis

First Advisor

Dr. Raid Al-Aqtash

Second Advisor

Dr. Avishek Mallick

Third Advisor

Dr. Alaa Elkadry

Abstract

The rapid expansion of the Internet of Things (IoT) has transformed modern computing by enabling seamless connectivity among heterogeneous devices across diverse application domains. However, this increased interconnectivity has significantly enlarged the attack surface of IoT networks, exposing them to a wide range of sophisticated cyber threats. Conventional security mechanisms often lack the capability to detect emerging attacks in real time, thereby necessitating the development of intelligent Intrusion Detection Systems (IDS) capable of accurately identifying malicious network activities. This study developed and evaluated a machine learning-based intrusion detection framework for multiclass IoT attack detection using the RT-IoT2022 dataset. The dataset was preprocessed by removing incomplete observations through complete-case analysis to ensure data quality. Information Gain feature selection was subsequently applied to identify and retain the most informative predictive attributes. To address the issue of class imbalance, the training data were balanced using random upsampling, while numerical features were standardized to improve model performance. Four supervised machine learning algorithms K-Nearest Neighbors (KNN), Random Forest (RF), Neural Network (NN), and Support Vector Machine (SVM) were implemented and evaluated using an 80:20 stratified train-test split. Model performance was assessed using confusion matrices and multiple evaluation metrics, including accuracy, precision, recall, specificity, F1-score, false positive rate, false negative rate, and balanced accuracy.

The findings of this study demonstrate that machine learning techniques provide an effective approach for intelligent intrusion detection in IoT environments, with ensemble learning methods, particularly Random Forest, offering superior classification performance and generalization on the RT-IoT2022 dataset. The proposed framework contributes to the advancement of IoT cybersecurity by providing a comprehensive comparative evaluation of widely used machine learning classifiers and offers practical guidance for researchers and cybersecurity practitioners in selecting suitable algorithms for real-time IoT intrusion detection applications.

Subject(s)

Mathematics.

Applied mathematics.

Statistics.

Computer security.

Machine learning.

Internet of things.

Computer networks -- Security measures.

Computer crimes.

Information theory.

Download

Share

COinS