EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A hyperbolic graph learning and structural entropy modeling approach for unknown anomaly detection in cross-domain networks

Xiaogang Yuan, Jiaxi Chen, Dezhi An

Journal of King Saud University Computer and Information Sciences · 2026-08 · 38 (6)

DOI: 10.1007/s44443-026-00906-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 05.06.2026. Verfasst von Xiaogang Yuan und 2 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, Gansu Provincial Higher Education Teachers' Innovation Fund, Lanzhou Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Network anomaly detection faces critical challenges in cross-domain scenarios where models trained on a labeled source domain fail on a target domain with different data distribution and scarce labels, especially for zero-day (unknown) attacks. Existing methods–including dynamic GNNs, unknown attack detectors, and domain adaptation techniques–suffer from Euclidean space assumptions, neglect of topological structure, or sensitivity to noisy pseudo-labels. To systematically address these limitations, we propose HGSER-GNN , a novel framework for cross-domain unknown network anomaly detection. It integrates three key innovations: (1) Hyperbolic graph representation learning that captures hierarchical network structures in the Poincaré ball space; (2) Continuous structural entropy (CSE) regularization that enhances generalization by aligning feature similarity with graph topology; and (3) Confidence-aware progressive pseudo-label learning that enables robust cross-domain adaptation through adaptive sample weighting and momentum-based label updates. Extensive experiments on three diverse datasets–CIC-IDS2017, CSE-CIC-IDS2018, and Cloud-DDoS-2024–demonstrate that HGSER-GNN significantly outperforms state-of-the-art baselines, including classic domain adaptation, deep one-class, and graph autoencoder methods. Our approach achieves an average F1-score improvement of 6.7%–35.7% over the strongest competitor and maintains strong detection capability even under 30% source label noise. Ablation studies and hyper-parameter sensitivity analyses confirm the synergy of all components. The model also demonstrates strong zero-day attack detection capability, as evidenced by per-class F1 scores and confusion matrices.

Förderung

  • Natural Science Foundation of China
  • Gansu Provincial Higher Education Teachers' Innovation Fund
  • Lanzhou Science and Technology Program
  • Anning District Science and Technology Program

Zitieren

APA

Yuan, X., Chen, J., & An, D. (2026). A hyperbolic graph learning and structural entropy modeling approach for unknown anomaly detection in cross-domain networks. Journal of King Saud University Computer and Information Sciences, 38(6). https://doi.org/10.1007/s44443-026-00906-0

Vancouver

Yuan X, Chen J, An D. A hyperbolic graph learning and structural entropy modeling approach for unknown anomaly detection in cross-domain networks. Journal of King Saud University Computer and Information Sciences. 2026;38(6). doi:10.1007/s44443-026-00906-0

BibTeX
@article{Yuan2026,
  author = {Yuan, Xiaogang and Chen, Jiaxi and An, Dezhi},
  title = {A hyperbolic graph learning and structural entropy modeling approach for unknown anomaly detection in cross-domain networks},
  journal = {Journal of King Saud University Computer and Information Sciences},
  year = {2026},
  volume = {38},
  number = {6},
  doi = {10.1007/s44443-026-00906-0}
}
Kostenlos starten →