EUVIMEDEUVIMED entdecken
Crossref

Detection and Prevention of DDoS Attacks Using Machine Learning Algorithms on Computer Networks

Nonot Wisnu Karyanto, Nia Saurina Saurina

International Journal of Research in Engineering and Modern Technology (IJREMTE) · 30.04.2026 · 3 (1) · 17-29

DOI: 10.30742/ijremte.v3i1.46 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Research in Engineering and Modern Technology (IJREMTE), online erschienen am 30.04.2026. Verfasst von Nonot Wisnu Karyanto und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The dynamic and unpredictable nature of Distributed Denial of Service (DDoS) attacks continues to pose a critical threat to the availability of computer network services. Traditional security measures, including static firewalls and signature-based intrusion detection systems, have proven inadequate for identifying novel attack variants whose traffic characteristics closely mimic legitimate network activity. To address this challenge, the present study introduces an automated framework for DDoS detection and mitigation, which is built upon machine learning algorithms. Four distinct algorithms were benchmarked in this study: Decision Tree, Random Forest, Support Vector Machine (SVM), and XGBoost. Among these, Random Forest delivered the most superior performance. When evaluated on a 20% hold-out test subset, this optimal model achieved an accuracy of 98.80%, precision of 98.51%, recall of 99.10%, and an F1-score of 98.80%. The exceptionally high recall rate confirms the model's effectiveness in capturing nearly all malicious traffic while maintaining an extremely low false-negative rate, whereas the high precision indicates a minimal occurrence of false alarms. The primary novelty of this work rests on the seamless integration of accurate machine-learning-based detection with empirically quantifiable automated mitigation responses—a holistic approach that remains rarely validated experimentally within a single cohesive framework. Consequently, this integrated strategy offers a highly adaptive and dependable solution for reinforcing network security and ensuring sustained service availability against the ever-evolving landscape of DDoS attacks.

Zitieren

APA

Karyanto, N. W., & Saurina, N. S. (2026). Detection and Prevention of DDoS Attacks Using Machine Learning Algorithms on Computer Networks. International Journal of Research in Engineering and Modern Technology (IJREMTE), 3(1), 17-29. https://doi.org/10.30742/ijremte.v3i1.46

Vancouver

Karyanto NW, Saurina NS. Detection and Prevention of DDoS Attacks Using Machine Learning Algorithms on Computer Networks. International Journal of Research in Engineering and Modern Technology (IJREMTE). 2026;3(1):17-29. doi:10.30742/ijremte.v3i1.46

BibTeX
@article{Karyanto2026,
  author = {Karyanto, Nonot Wisnu and Saurina, Nia Saurina},
  title = {Detection and Prevention of DDoS Attacks Using Machine Learning Algorithms on Computer Networks},
  journal = {International Journal of Research in Engineering and Modern Technology (IJREMTE)},
  year = {2026},
  volume = {3},
  number = {1},
  pages = {17--29},
  doi = {10.30742/ijremte.v3i1.46}
}
Kostenlos starten →