Real-Time Detection of IoT Cyber Threats using Advanced Deep Learning Methods

Gharpure, Tushar Rajesh (2025) Real-Time Detection of IoT Cyber Threats using Advanced Deep Learning Methods. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (585kB) | Preview

Abstract

The growth of the Internet of Things (IoT) has disrupted modern industry but has also exposed networks to an expanding range of cyber threats. Resource-constrained IoT devices, often deployed in unsecured and heteronomous systems, are inherently vulnerable to exploitation via Distributed Denial of Service (DDoS), brute-force intrusion, and malicious scanning. Conventional intrusion detection systems (IDS) lack sufficient flexibility or processing power to address these vulnerabilities by relying on predefined signatures of malicious activity and requiring a reengineering process to adapt to new and evolving issues. In this study, we proposed a deep learning (DL) based intrusion detection framework for IoT security using three architectures (Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a hybrid Convolutional LSTM (Conv-LSTM) model). Experimental results demonstrated that both CNN and LSTM offered poor or decreased performance when compared to the Conv-LSTM model. When evaluating the hybrid Conv-LSTM model under the experimental framework based upon the benchmark IoT dataset, the Conv-LSTM model accomplished near-perfect accuracy, precision, recall, and F1-score, and significantly lower false positive and false negative detections. The proposed framework was also deployed as a real-time web application capable not only of live traffic monitoring but also of providing immediate notification of threats in real-time. Overall, my findings support the claim that the Conv-LSTM model architecture provides a high-performance, scalable, and beyond a doubt accurate approach to next-generation IoT intrusion detection.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Shubhnil, Shubham UNSPECIFIED
Subjects:	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:	01 Jul 2026 10:38
Last Modified:	01 Jul 2026 10:38
URI:	https://norma.ncirl.ie/id/eprint/9428

Actions (login required)

View Item