EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Feature Selection for Improving ANN and CNN Models for Attack Detection in Zeek Network Data

Sikha S. Bagui, Mohamed Elbatouty, Dustin Mink, Subhash C. Bagui

Future Internet · 24.06.2026 · 18 (7) · 333

DOI: 10.3390/fi18070333 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 24.06.2026. Verfasst von Sikha S. Bagui und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the past few years, cyber-attacks have risen at an exponential rate across all sectors, and both private and public institutions have faced increasingly sophisticated threats. As this upward trend continues, the need for advanced and efficient threat detection systems is essential. This paper investigates the use of feature importance (FI) Coefficients to improve Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) models, leveraging feature selection to enhance model interpretability and optimize performance. By systematically filtering out the weaker features, we examine the reduced features’ impact on model accuracy, precision, recall, and F1 score. Experiments were conducted on two new datasets, UWF-ZeekDataSum2025-1 and UWF-ZeekDataSum2025-2, using a baseline ANN/CNN architecture and multiple architectural variants. The results on UWF-ZeekDataSum2025-1 show a clear performance gain for certain feature importance thresholds, with models such as ANN-Minimal, ANN-Overfit-Wide, ANN-Shallow-Low-Optimization, CNN-Shallow, and CNN-Very-Shallow outperforming the baseline after reducing the feature space from seventeen features to fewer than four. For UWF-ZeekDataSum2025-2, improvements occur across a broader range of thresholds, with models including ANN-Deep-Sub-Conv, ANN-Shallow-Low-Opt, CNN-Shallow, CNN-Very-Shallow, and ANN-Minimal exceeding 95% performance around the 0.25–0.28 thresholds, with additional gains at 0.31–0.32 for some architectures. These findings demonstrate that by strategically leveraging feature importance coefficient thresholds, we can significantly enhance neural network intrusion detection systems, offering a reproducible pathway for adapting these methods on similar environments.

Zitieren

APA

Bagui, S. S., Elbatouty, M., Mink, D., & Bagui, S. C. (2026). Feature Selection for Improving ANN and CNN Models for Attack Detection in Zeek Network Data. Future Internet, 18(7), 333. https://doi.org/10.3390/fi18070333

Vancouver

Bagui SS, Elbatouty M, Mink D, Bagui SC. Feature Selection for Improving ANN and CNN Models for Attack Detection in Zeek Network Data. Future Internet. 2026;18(7):333. doi:10.3390/fi18070333

BibTeX
@article{Bagui2026,
  author = {Bagui, Sikha S. and Elbatouty, Mohamed and Mink, Dustin and Bagui, Subhash C.},
  title = {Feature Selection for Improving ANN and CNN Models for Attack Detection in Zeek Network Data},
  journal = {Future Internet},
  year = {2026},
  volume = {18},
  number = {7},
  pages = {333},
  doi = {10.3390/fi18070333}
}
Kostenlos starten →