EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unlocking Few-Shot Encrypted Traffic Classification: A Contrastive-Driven Meta-Learning Approach

Zheng Li, Jian Wang, Ya-Fei Song, Shao-Hua Yue

Electronics · 30.10.2025 · 14 (21) · 4245

DOI: 10.3390/electronics14214245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 30.10.2025. Verfasst von Zheng Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The classification of encrypted traffic is critical for network security, yet it faces a significant “few-shot” challenge as novel applications with scarce labeled data continuously emerge. This complexity arises from the high-dimensional, noisy nature of traffic data, making it difficult for models to generalize from few examples. Existing paradigms, such as meta-learning from scratch or standard pre-train/fine-tune methods, often fail in this scenario. To address this gap, we propose Contrastive Learning Meta-Flow (CL-MetaFlow), a novel two-stage learning framework that uniquely synergizes the strengths of contrastive representation learning and meta-learning adaptation. In the first stage, a robust feature encoder is pre-trained using supervised contrastive learning on known traffic classes, shaping a highly discriminative and metric-friendly embedding space. In the second stage, this pre-trained encoder initializes a Prototypical Network, enabling rapid and effective adaptation to new, unseen classes from only a few samples. Extensive experiments on a benchmark dataset (ISCX-VPN-2016 & ISCX-Tor-2017) demonstrate the superiority of our approach. Notably, in a five-way five-shot setting, CL-MetaFlow achieves a Macro F1-Score of 0.620, significantly outperforming from-scratch ProtoNet (0.384), a standard fine-tuning baseline (0.160), and strong pre-training counterparts like SimCLR+ProtoNet (0.545) and a re-implemented T-Sanitation (0.591). Our work validates that a high-quality, domain-adapted feature prior is the key to unlocking high-performance few-shot learning in complex network environments, providing a practical and powerful solution for real-world traffic analysis.

Zitieren

APA

Li, Z., Wang, J., Song, Y., & Yue, S. (2025). Unlocking Few-Shot Encrypted Traffic Classification: A Contrastive-Driven Meta-Learning Approach. Electronics, 14(21), 4245. https://doi.org/10.3390/electronics14214245

Vancouver

Li Z, Wang J, Song Y, Yue S. Unlocking Few-Shot Encrypted Traffic Classification: A Contrastive-Driven Meta-Learning Approach. Electronics. 2025;14(21):4245. doi:10.3390/electronics14214245

BibTeX
@article{Li2025,
  author = {Li, Zheng and Wang, Jian and Song, Ya-Fei and Yue, Shao-Hua},
  title = {Unlocking Few-Shot Encrypted Traffic Classification: A Contrastive-Driven Meta-Learning Approach},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {21},
  pages = {4245},
  doi = {10.3390/electronics14214245}
}
Kostenlos starten →