Analyzing Machine Learning Model Synergies for Next- Generation IoT Malware Detection: A BERT and GPT Integration Approach

Lagadapati, Prahaladh (2025) Analyzing Machine Learning Model Synergies for Next- Generation IoT Malware Detection: A BERT and GPT Integration Approach. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The proliferation of the Internet of Things (IoT) has resulted in significant security threats, with malware attacks rising by 62% annually, of which polymorphic variants constitute 41% of the total threats identified. The present study proposes a novel hybrid framework combining ModernBERT and GPT-3.5 embeddings to enhance IoT malware detection mechanisms. This study converts network traffic characteristics into semantic textual formats, facilitating transformer-based analysis of behavioural patterns. The systematic evaluation of the CIC IoT 2023 dataset, which includes 80,000 balanced samples across five attack categories, demonstrates that the hybrid approach attains an overall accuracy of 84.2%, reflecting a 71.5% enhancement compared to traditional methods. The system exhibits high efficacy in identifying DDoS attacks, achieving a 99.7% F1-score, and network attacks, with a 95.7% F1-score. However, it faces difficulties in reconnaissance detection, reflected in a 54.8% F1-score. Feature-level fusion of statistical, probabilistic, and semantic representations demonstrates superiority over single-model approaches, with embedding features accounting for 73% of decision importance. This paper demonstrates the promise of applying effective transformers and semantic embeddings to IoT security with a system that provides performance-balanced detection with the computational realities characteristic of IoT environments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rifai, Hicham 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 11:35
Last Modified:	01 Jul 2026 11:35
URI:	https://norma.ncirl.ie/id/eprint/9436

Actions (login required)

View Item