EUVIMEDEUVIMED entdecken
Crossref

Detection of Cyber Attacks in Critical Infrastructure Systems Using Deep Learning Approaches

Hamza Talha Gümüş, Mustafa Yasin Erten, Hüseyin Aydilek

Periodica Polytechnica Electrical Engineering and Computer Science · 08.06.2026 · 70 (1) · 42-51

DOI: 10.3311/ppee.43471 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Periodica Polytechnica Electrical Engineering and Computer Science, online erschienen am 08.06.2026. Verfasst von Hamza Talha Gümüş und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring the security of industrial control systems (ICS) and cyber-physical systems (CPS) is increasingly challenging due to the integration of real-time data flows, interconnected sensors, and evolving cyber threats. This study presents a comparative evaluation of five deep learning architectures – CNN1D, CNN-LSTM, AE-CNN, GNN-CNN, and AutoGraph-TConv – across six heterogeneous datasets: SWaT, BATADAL, BoT-IoT, EUROPEC, MEDSEC, and MSCAD. Unlike many previous studies that focus on a single model or dataset, a unified benchmarking framework is employed to assess model generalizability across diverse ICS environments. The experimental pipeline incorporates standardized preprocessing, normalization, chronological data splitting, and multi-metric evaluation using Accuracy, Precision, Recall, F1-score, AUROC, and AUPRC. Results demonstrate that dataset characteristics significantly influence model performance. Reconstruction-based architectures, particularly AE-CNN, show greater effectiveness on physical-process datasets such as SWaT, while graph-temporal architectures provide superior performance on network-centric datasets. AE-CNN achieved the highest F1-score of 0.509 on SWaT, CNN1D achieved an F1-score of 0.620 on BATADAL, CNN-LSTM achieved an F1-score of 0.935 on EUROPEC, and graph-temporal models (AutoGraph-TConv and GNN-CNN) attained near-perfect performance (F1 ≈ 1.000) on BoT-IoT, MEDSEC, and MSCAD. The findings indicate that data separability and process complexity are key factors influencing anomaly detection performance. Rather than proposing a new architecture, this work provides a comprehensive benchmarking framework that clarifies the relationship between dataset characteristics and model suitability for ICS anomaly detection.

Zitieren

APA

Gümüş, H. T., Erten, M. Y., & Aydilek, H. (2026). Detection of Cyber Attacks in Critical Infrastructure Systems Using Deep Learning Approaches. Periodica Polytechnica Electrical Engineering and Computer Science, 70(1), 42-51. https://doi.org/10.3311/ppee.43471

Vancouver

Gümüş HT, Erten MY, Aydilek H. Detection of Cyber Attacks in Critical Infrastructure Systems Using Deep Learning Approaches. Periodica Polytechnica Electrical Engineering and Computer Science. 2026;70(1):42-51. doi:10.3311/ppee.43471

BibTeX
@article{Gm2026,
  author = {Gümüş, Hamza Talha and Erten, Mustafa Yasin and Aydilek, Hüseyin},
  title = {Detection of Cyber Attacks in Critical Infrastructure Systems Using Deep Learning Approaches},
  journal = {Periodica Polytechnica Electrical Engineering and Computer Science},
  year = {2026},
  volume = {70},
  number = {1},
  pages = {42--51},
  doi = {10.3311/ppee.43471}
}
Kostenlos starten →