Evaluating the Effectiveness of Neural Networks for Cyber Attack Detection in IoT Ecosystems

Daniel, Lyuble (2025) Evaluating the Effectiveness of Neural Networks for Cyber Attack Detection in IoT Ecosystems. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The introduction of Internet of Things (IoT) devices into the critical infrastructures has resulted in a greatly increased attack surface and the need of an Intrusion Detection Systems that are able to deliver in real time. This research explores the usefulness of Artificial Neural Networks (ANN) and Long ShortTerm Memory (LSTM) in identifying various IoT-specific attacks. It compares ANN and LSTM with common machine learning algorithms such as Random Forest (RF), XGBoost, and Support Vector Machine (SVM) using the standard CICIoT2023 dataset like the environment of a real-world traffic in 105 IoT devices. Data preprocessing, class balancing using Synthetic Minority Oversampling Technique (SMOTE) and hyperparameter optimization were used. The evaluation metrics were accuracy, precision, recall, F1- score, Area Under the Curve (AUC) and time to execute. It has been shown that RF provided the best scores with 95 percent accuracy during the test and an almost perfect AUC value of 0.9992, whereas LSTM achieved 77 percent and 0.96 on AUC, which indicates better temporal pattern recognition of this approaches. ANN performed mediocrity with 0.94 AUC and 69 percent accuracy. The results indicate that ANN and LSTM show a great potential in learning the complex behavior of traffic yet, at the same time, the traditional machine learning, and in particular the RF, offers a very useful result in detecting IoT attacks in a manageable amount of computing resources.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cortés-Mendoza, Jorge Mario UNSPECIFIED
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing 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
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	20 Mar 2026 14:48
Last Modified:	20 Mar 2026 14:48
URI:	https://norma.ncirl.ie/id/eprint/9206

Actions (login required)

View Item