EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Data-Centric Network Traffic Dataset for Anomaly Detection: Construction, Reproducible Pipeline, and Technical Validation

Daniel Quirumbay Yagual, Diego Fernández Iglesias, Francisco J. Nóvoa, Daniel Garabato

Data · 06.08.2026 · 11 (8) · 199

DOI: 10.3390/data11080199 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data, online erschienen am 06.08.2026. Verfasst von Daniel Quirumbay Yagual und 3 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science, Innovation and Universities (MICIU), the State Research Agency, European Regional Development Fund (ERDF), European Unio.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The effectiveness of machine learning and deep learning methods for network anomaly detection depends strongly on the quality and representativeness of the datasets used for training and evaluation. Despite recent advances, many publicly available benchmarks rely on synthetic traffic, outdated attack scenarios, or limited representation of encrypted communications. This work presents a network traffic dataset derived from operational firewall logs collected in a heterogeneous institutional environment dominated by HTTPS/TLS traffic. A structured data-centric pipeline was implemented, including preprocessing, behavioral feature engineering, unsupervised pseudo-labeling through the EFMS–KMeans algorithm, class balancing using SMOTE, and the generation of model-oriented sequential representations for deep learning analysis. The resulting dataset contains large-scale flow-level records describing volumetric, behavioral, and temporal traffic characteristics while preserving privacy through anonymization procedures. Technical validation was conducted using statistical analysis, entropy-based measurements, clustering quality metrics, and dimensionality reduction techniques, confirming data consistency, structural diversity, and class separability. The dataset is publicly available through the Mendeley Data repository together with metadata and documentation supporting anomaly detection research, encrypted traffic analysis, and the evaluation of machine learning and deep learning approaches in realistic cybersecurity environments.

Förderung

  • Ministry of Science, Innovation and Universities (MICIU), the State Research Agency
  • European Regional Development Fund (ERDF), European Unio

Zitieren

APA

Yagual, D. Q., Iglesias, D. F., Nóvoa, F. J., & Garabato, D. (2026). A Data-Centric Network Traffic Dataset for Anomaly Detection: Construction, Reproducible Pipeline, and Technical Validation. Data, 11(8), 199. https://doi.org/10.3390/data11080199

Vancouver

Yagual DQ, Iglesias DF, Nóvoa FJ, Garabato D. A Data-Centric Network Traffic Dataset for Anomaly Detection: Construction, Reproducible Pipeline, and Technical Validation. Data. 2026;11(8):199. doi:10.3390/data11080199

BibTeX
@article{Yagual2026,
  author = {Yagual, Daniel Quirumbay and Iglesias, Diego Fernández and Nóvoa, Francisco J. and Garabato, Daniel},
  title = {A Data-Centric Network Traffic Dataset for Anomaly Detection: Construction, Reproducible Pipeline, and Technical Validation},
  journal = {Data},
  year = {2026},
  volume = {11},
  number = {8},
  pages = {199},
  doi = {10.3390/data11080199}
}
Kostenlos starten →