EUVIMEDEUVIMED entdecken
Crossref

GT 2 D: Unifying Temporal Dynamics and Spatial Topology for Encrypted Traffic Anomaly Detection

Zhongqi Miao, Lixing Chen, Yang Bai, Zhe Qu, Pan Zhou, Heqiang Wang, Youqi Li

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 11358-11369

DOI: 10.1109/tccn.2026.3711089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Zhongqi Miao und 6 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hainan Province, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Encrypted traffic anomaly detection is critical for modern network security yet remains challenging due to the coupling of data privacy and intricate attack patterns. While recent advancements, particularly pre-trained models, effectively extract features by treating traffic bytes as textual sequences, they predominantly focus on intra-flow content representation. Consequently, these approaches often neglect the topological spatial structure of network interactions, failing to capture the collateral impact of attacks across communicating entities. To bridge this gap, we redefine the paradigm of encrypted traffic analysis by constructing a dynamic encrypted traffic time series graph, where IP addresses serve as vertices and traffic flows act as edges. On this basis, we propose GT2D (Graph Time Series Transformer-based Malicious Traffic Detector), a novel framework that unifies temporal dynamics with spatial topology. GT2D introduces a vertex decoupling repair mechanism that segments univariate flow time series into subsequence-level patches, enabling Transformer encoder to extract fine-grained local temporal patterns. To capture topological dependencies, we design a cross-vertex multivariate representation module that re-associates these temporal features with IP vertices, augmented by Laplacian positional encodings and refined via Graph Convolutional Networks. Extensive experiments on real-world datasets demonstrate the superiority of our framework. GT2D outperforms state-of-the-art baselines with a maximum F1-score improvement of 3.74% and a recall improvement of 6.02%, proving its robustness in identifying complex anomalies through joint spatio-temporal modeling.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hainan Province
  • Beijing Natural Science Foundation
  • Beijing Institute of Technology Research Fund Program for Young Scholars

Zitieren

APA

Miao, Z., Chen, L., Bai, Y., Qu, Z., Zhou, P., Wang, H., & Li, Y. (2026). GT 2 D: Unifying Temporal Dynamics and Spatial Topology for Encrypted Traffic Anomaly Detection. IEEE Transactions on Cognitive Communications and Networking, 12, 11358-11369. https://doi.org/10.1109/tccn.2026.3711089

Vancouver

Miao Z, Chen L, Bai Y, Qu Z, Zhou P, Wang H, et al. GT 2 D: Unifying Temporal Dynamics and Spatial Topology for Encrypted Traffic Anomaly Detection. IEEE Transactions on Cognitive Communications and Networking. 2026;12:11358-11369. doi:10.1109/tccn.2026.3711089

BibTeX
@article{Miao2026,
  author = {Miao, Zhongqi and Chen, Lixing and Bai, Yang and Qu, Zhe and Zhou, Pan and Wang, Heqiang and Li, Youqi},
  title = {GT 2 D: Unifying Temporal Dynamics and Spatial Topology for Encrypted Traffic Anomaly Detection},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {11358--11369},
  doi = {10.1109/tccn.2026.3711089}
}
Kostenlos starten →