Federated Learning for DDoS Attack Detection in Cloud Computing: A Review of Privacy-Preserving and Scalable Security Approaches
Scholar J · 2026
DOI: 10.67378/t75njb85 ↗Kurz gefasst
Fachartikel in der Zeitschrift Scholar J, 2026. Verfasst von M. Usman und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study examines critical issues in cloud-based cybersecurity, focusing on the application of machine learning and privacy-preserving techniques for Distributed Denial of Service (DDoS) detection. It evaluates existing approaches to DDoS mitigation, emphasizing the scalability and real-time challenges encountered in dynamic cloud environments. The research further explores federated learning, homomorphic encryption, and differential privacy as emerging methods for decentralized and secure data analysis. By integrating insights from recent studies, the work highlights both the limitations of current detection frameworks and the potential of advanced learning paradigms to enhance security and scalability. The findings contribute to developing robust, privacy-conscious, and adaptive DDoS detection models suitable for modern cloud infrastructures.
Zitieren
APA
Usman, M., Olalere, M., & Ajayi, B. (2026). Federated Learning for DDoS Attack Detection in Cloud Computing: A Review of Privacy-Preserving and Scalable Security Approaches. Scholar J. https://doi.org/10.67378/t75njb85
Vancouver
Usman M, Olalere M, Ajayi B. Federated Learning for DDoS Attack Detection in Cloud Computing: A Review of Privacy-Preserving and Scalable Security Approaches. Scholar J. 2026. doi:10.67378/t75njb85
BibTeX
@article{Usman2026,
author = {Usman, M. and Olalere, M. and Ajayi, B.A.},
title = {Federated Learning for DDoS Attack Detection in Cloud Computing: A Review of Privacy-Preserving and Scalable Security Approaches},
journal = {Scholar J},
year = {2026},
doi = {10.67378/t75njb85}
}
EUVIMED