Abstract
In an increasingly interconnected world, cybersecurity threats have become more sophisticated, necessitating advanced, scalable, and privacy-preserving solutions. MetaGuard emerges as a novel framework that integrates federated learning with hybrid machine learning models, specifically XGBoost and meta-learning, to enhance proactive cyber threat detection. This framework offers a robust, distributed approach to cybersecurity, ensuring high detection accuracy while preserving user privacy through the implementation of differential privacy and homomorphic encryption. MetaGuard leverages distributed nodes to collaboratively train a global model, enabling rapid adaptation to new threats without the need for centralized data aggregation. Experimental evaluations using the CYBER-2024 dataset demonstrate that MetaGuard significantly outperforms traditional centralized models and contemporary federated learning frameworks, with notable improvements in accuracy (by 5%), precision (by 4.7%), recall (by 4.5%), and F1-score (by 4.9%). Despite challenges such as potential computational overhead and communication latency, MetaGuard’s scalability and privacy-preserving features establish it as a highly effective solution for addressing modern cybersecurity challenges. Future research will focus on optimizing the federated learning process, integrating additional machine learning techniques, and expanding the framework’s applications across various industries.
Recommended Citation
Al-Khalisy, Shatha H. Jafer and Al-Kateb, Ghada Emad
(2025)
"MetaGuard: A Federated Learning Approach to Hybrid XGBoost and Meta-Learning Models for Proactive Cyber Threat Hunting,"
Iraqi Journal for Computer Science and Mathematics: Vol. 6:
Iss.
3, Article 27.
DOI: https://doi.org/10.52866/2788-7421.1300
Available at:
https://ijcsm.researchcommons.org/ijcsm/vol6/iss3/27
