Enhancing IoT Network Traffic Anomaly Detection with GANs

Mutra, Durga Prasad Reddy (2024) Enhancing IoT Network Traffic Anomaly Detection with GANs. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The rapid proliferation of IoT devices has been introducing unprecedented challenges in the context of security, especially around the detection of network traffic anomalies in highly imbalanced datasets. The work proposes a new approach to detecting IoT network traffic anomalies with conditional generative adversarial networks and focuses on the challenge posed by an extremely imbalanced class problem where attack patterns take about 97.69%, while benign constitutes about 2.31% of the entire traffic. This paper used the NF-BoT-IoT dataset with a balanced sampling strategy and sophisticated feature engineering for IP addresses and port numbers. With this GAN-based architecture incorporating batch normalization and adaptive learning rates, it yields an accuracy of 97.40% on the real data, which, of course, is impressive in comparison to the random forest baseline of 94.74%.Importantly, the GAN approach reduced FPs from 10 to 4.4% when attaining high attack detection accuracy in various scenarios. The carried-out study contributes to the field by handling class imbalance in network security data with a novel approach and in proving the practical viability of GAN-based techniques in IoT security. Results show that hybrid implementations can provide the efficiency of traditional methods combined with advanced detection capabilities of GANs, especially in critical infrastructure protection, where accuracy and adaptability are paramount.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Singh, Jaswinder UNSPECIFIED
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 Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2025 14:33
Last Modified:	03 Sep 2025 14:33
URI:	https://norma.ncirl.ie/id/eprint/8754

Actions (login required)

View Item