EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Confidence-Gated Prototype-Guided Graph Contrastive Learning for Semi-Supervised Encrypted Traffic Classification

Yixuan Xin, Zhe Wu, Qian Deng, Xiaodong Zang

Computers · 2026-11-17 · 15 (11) · 847

DOI: 10.3390/computers15110847 ↗

At a glance

Journal article in Computers, published online on 2026-11-17. Written by Yixuan Xin and 3 co-authors. 39 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, China.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Most existing encrypted traffic classification methods treat each traffic flow as an independent sample, overlooking the relationships shared by similar flows. This can amplify within-class variation and increase class overlap, especially when distinguishing characteristics are subtle and labeled data are limited. To address this problem, we propose PGCL-CG, a prototype-guided semi-supervised graph contrastive learning framework. We represent flow-level statistical features as a sparse, weighted k-nearest-neighbor graph and use GraphSAGE to aggregate information from neighboring flows and to capture their underlying structural relationships. We pretrain the encoder using self-supervised graph contrastive learning to obtain stable representations. We use a student–teacher architecture to produce more stable pseudo-labels and apply hierarchical density-based spatial clustering to filter out low-confidence assignments. We conduct extensive experiments on the two open datasets, demonstrating that PGCL-CG outperforms competitive baselines and remains robust even when only a small fraction of labels (e.g., 20% or 40%) is available. In particular, with only 5% of the training flows labeled, PGCL-CG achieves F1 scores of 0.820 and 0.771 on the ISCX-VPN and ISCX-nonVPN subsets, respectively, demonstrating its effectiveness under limited supervision.

Funding

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shandong Province, China

Cite

APA

Xin, Y., Wu, Z., Deng, Q., & Zang, X. (2026). Confidence-Gated Prototype-Guided Graph Contrastive Learning for Semi-Supervised Encrypted Traffic Classification. Computers, 15(11), 847. https://doi.org/10.3390/computers15110847

Vancouver

Xin Y, Wu Z, Deng Q, Zang X. Confidence-Gated Prototype-Guided Graph Contrastive Learning for Semi-Supervised Encrypted Traffic Classification. Computers. 2026;15(11):847. doi:10.3390/computers15110847

BibTeX
@article{Xin2026,
  author = {Xin, Yixuan and Wu, Zhe and Deng, Qian and Zang, Xiaodong},
  title = {Confidence-Gated Prototype-Guided Graph Contrastive Learning for Semi-Supervised Encrypted Traffic Classification},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {847},
  doi = {10.3390/computers15110847}
}
Start for free →