The NIDS Framework for Identifying Anomalous Traffic in IoT

Poswal, Vipin (2025) The NIDS Framework for Identifying Anomalous Traffic in IoT. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (782kB) | Preview

Abstract

As cyber threats intensify across the rapidly expanding Internet of Things (IoT), safeguarding with cyber threats over the largely expanding IoT on the rise, the protection of the resource-limited and heterogeneous devices has become an operational necessity. The recent advanced attacks are exploiting elements of normal traffic to perform some novel, stealthy attacks and traditional perimeter-based defences (e.g., authentication and firewalls) have difficulty recognizing these types of attacks. The thesis proposes a low overhead Network Intrusion Detection System that is specially designed to work with IoT and tests it on the IoT Network Intrusion Dataset (IoTID20). The methodology follows a Knowledge Discovery in Databases (KDD) oriented workflow with rigorous data preprocessing. Three models of classifier, Random Forest (RF), Artificial Neural Network (ANN), and K-Nearest Neighbors (KNN), are trained and compared to balance the effectiveness of balancing and computational efficiency that can fit in edge implementation. Evaluation of performance is done based on the standard metrics in the literature. The experimental findings prove that the designed RF-based model scored the most in the IoTID20 dataset with the highest accuracy of 98% and F1-score of 0.98. The Experiment results show that RF outperformed the state-of-the-art by 1.2% in accuracy, achieving the best performance in real-time intrusion detection for IoT contexts.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cortes Mendoza, Jorge Mario UNSPECIFIED
Uncontrolled Keywords:	NIDS; IoT Security; Random Forest (RF); Artificial Neural Network (ANN); K-Nearest Neighbors (KNN); PCA; Knowledge Discovery in Databases (KDD); Dataset IoTID20
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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	30 Mar 2026 13:40
Last Modified:	30 Mar 2026 13:40
URI:	https://norma.ncirl.ie/id/eprint/9255

Actions (login required)

View Item