Anomaly Detection in 6G Networks Using Large Language Models (LLMs)
Abasi, Ammar Kamal Aloqaily, Moayad Guizani, Mohsen
Abasi, Ammar Kamal
Aloqaily, Moayad
Guizani, Mohsen
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The anticipated deployment of 6G networks by 2030 is expected to introduce advanced capabilities, such as ultra-low latency and massive device connectivity, thereby increasing the complexity of potential security threats. Traditional anomaly detection methods, primarily based on Ensemble Learning (EL) classifiers, often lack the adaptability required to address evolving cyber threats and zero-day attacks. This paper proposes a novel approach that leverages Large Language Models (LLMs) to enhance anomaly detection in 6G networks. By transforming structured network traffic data into natural language descriptions, LLMs can be fine-tuned to effectively identify anomalous patterns. Experimental evaluations demonstrate that this LLM-based method outperforms traditional EL classifiers in terms of recall, precision, and adaptability to unforeseen threats, marking a significant advancement in AI-driven network security.
Citation
A. K. Abasi, M. Aloqaily and M. Guizani, "Anomaly Detection in 6G Networks Using Large Language Models (LLMs)," 2025 International Wireless Communications and Mobile Computing (IWCMC), Abu Dhabi, United Arab Emirates, 2025, pp. 1466-1471, doi: 10.1109/IWCMC65282.2025.11059535.
Source
Proceedings of the International Wireless Communications and Mobile Computing
Conference
2025 International Wireless Communications and Mobile Computing (IWCMC), 2025
Keywords
6G Networks, Anomaly Detection, Large Language Models (LLMs), Network Security, Ensemble Learning
Subjects
Source
2025 International Wireless Communications and Mobile Computing (IWCMC), 2025
Publisher
IEEE