EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust Network Intrusion Detection Using Deep Stacking Ensembles and Hybrid Feature Selection

Shahad Aman Ibrahim

Iraqi Journal of Communications and Computer Networks · 25.03.2026 · 2 (1) · 19-26

DOI: 10.58564/ijccn.2.1.2026.14 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Iraqi Journal of Communications and Computer Networks, online erschienen am 25.03.2026. Verfasst von Shahad Aman Ibrahim. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the contemporary networked systems, network security has emerged to be a critical issue. Intrusion Detection Systems (IDS) are imperative defense systems that can be used to detect malicious network traffic. The study provides a new IDS model, which combines various machine learning models and deep learning architectures to generate better detection accuracy on the NSL-KDD benchmark data. The researchers make four main contributions: (1) a hybrid approach to feature selection which involves Information Gain and correlation-based redundancy elimination, (2) Synthetic Minority Oversampling Technique (SMOTE) to overcome the class imbalance, (3) a stacking ensemble classifier, and (4) a Deep Neural Network (DNN) with Batch Normalization, LeakyReLU activation, and Dropout regularization. Through experiment, it has been shown that the proposed stacking ensemble has an accuracy of 99.80 and an F1-score of 0.998 on binary classification, and 99.53 and five attack categories on multi-class classification. The proposed strategy is much better than individual baseline classifiers and has strong detection ability of minority attack classes such as R2L and U2R attacks.

Zitieren

APA

Ibrahim, S. A. (2026). Robust Network Intrusion Detection Using Deep Stacking Ensembles and Hybrid Feature Selection. Iraqi Journal of Communications and Computer Networks, 2(1), 19-26. https://doi.org/10.58564/ijccn.2.1.2026.14

Vancouver

Ibrahim SA. Robust Network Intrusion Detection Using Deep Stacking Ensembles and Hybrid Feature Selection. Iraqi Journal of Communications and Computer Networks. 2026;2(1):19-26. doi:10.58564/ijccn.2.1.2026.14

BibTeX
@article{Ibrahim2026,
  author = {Ibrahim, Shahad Aman},
  title = {Robust Network Intrusion Detection Using Deep Stacking Ensembles and Hybrid Feature Selection},
  journal = {Iraqi Journal of Communications and Computer Networks},
  year = {2026},
  volume = {2},
  number = {1},
  pages = {19--26},
  doi = {10.58564/ijccn.2.1.2026.14}
}
Kostenlos starten →