6G mmWave Security Advancements through Federated Learning and Differential Privacy
Abasi, Ammar Kamal Aloqaily, Moayad Guizani, Mohsen
Abasi, Ammar Kamal
Aloqaily, Moayad
Guizani, Mohsen
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
This paper presents a new framework that integrates Federated Learning (FL) with advanced privacy-preserving mechanisms to enhance the security of millimeter-wave (mmWave) beam prediction systems in 6G networks. By decentralizing model training, the framework safeguards sensitive user information while maintaining high model accuracy, effectively addressing privacy concerns inherent in centralized Machine learning (ML) methods. Adaptive noise augmentation and differential privacy principles are incorporated to mitigate vulnerabilities in FL systems, providing a robust defense against adversarial threats such as the Fast Gradient Sign Method (FGSM). Extensive experiments across diverse scenarios, including adversarial attacks, outdoor environments, and indoor settings, demonstrate a significant 17.45% average improvement in defense effectiveness, underscoring the frameworkâs ability to ensure data integrity, privacy, and performance reliability in dynamic 6G environments. By seamlessly integrating privacy protection with resilience against adversarial attacks, the proposed solution offers a comprehensive and scalable approach to secure mmWave communication systems. This work establishes a critical foundation for advancing secure 6G networks and sets a benchmark for future research in decentralized, privacy-aware machine learning systems.
Citation
A. K. Abasi, M. Aloqaily and M. Guizani, "6G mmWave Security Advancements through Federated Learning and Differential Privacy," in IEEE Transactions on Network and Service Management, doi: 10.1109/TNSM.2025.3528235.
Source
IEEE Transactions on Network and Service Management
Conference
Keywords
Millimeter wave communication, 6G mobile communication, Data models, Array signal processing, Security, Predictive models, Adaptation models, Accuracy, Training, Privacy
Subjects
Source
Publisher
IEEE