EUVIMEDEUVIMED entdecken
Crossref

A Distributed Federated Intelligence Model for Real-Time DDoS Attack Detection in SDN Environments

D. Vengaimarbhan, P. Venkatraman, A. P. Rishi Kumar

International Journal of Drug Delivery Technology · 02.06.2026 · 16 (44s)

DOI: 10.25258/ijddt.16.44s.68 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 02.06.2026. Verfasst von D. Vengaimarbhan und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Software Defined Networking (SDN) offers improved management capabilities by allowing control and data planes to operate independently. This decoupling allows for greater flexibility and overall ease of configuration, but it also introduces a significant vulnerability into the SDN ecosystem: the SDN controller becomes a focal point for attackers using a Distributed Denial of Service (DDoS) attack against this vital control plane. A DDoS attack against the control plane will create resource exhaustion at the SDN controller, which can lead to performance degradation, delays in packet processing or complete service disruptions. The commonly used methods for detecting DDoS attacks using centralized machine learning algorithms may not scale well and may produce excessive overhead related to communication with each controller in an SDN system, particularly in large, multi-controller SDN deployments. Although recent advances in federated learning provide enhanced capabilities for privacy and distribution of statistical models, the vast majority of these approaches are based primarily on traffic-based features and attempt to collect data based on fixed time intervals. This study proposes a new control--plane-aware federated learning architecture to improve adaptive DDoS attack detection within distributed SDN systems, using local traffic metrics related to the SDN operation, including packet-in rates, flow miss ratios, controller processing delays, and overall system performance metrics. Rather than synchronizing model gathering and aggregation based upon fixed time intervals, models will utilize adaptive aggregation based on an emerging condition within the operating environment.

Zitieren

APA

Vengaimarbhan, D., Venkatraman, P., & Kumar, A. P. R. (2026). A Distributed Federated Intelligence Model for Real-Time DDoS Attack Detection in SDN Environments. International Journal of Drug Delivery Technology, 16(44s). https://doi.org/10.25258/ijddt.16.44s.68

Vancouver

Vengaimarbhan D, Venkatraman P, Kumar APR. A Distributed Federated Intelligence Model for Real-Time DDoS Attack Detection in SDN Environments. International Journal of Drug Delivery Technology. 2026;16(44s). doi:10.25258/ijddt.16.44s.68

BibTeX
@article{Vengaimarbhan2026,
  author = {Vengaimarbhan, D. and Venkatraman, P. and Kumar, A. P. Rishi},
  title = {A Distributed Federated Intelligence Model for Real-Time DDoS Attack Detection in SDN Environments},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {44s},
  doi = {10.25258/ijddt.16.44s.68}
}
Kostenlos starten →