EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing network traffic detection via interpolation augmentation and contrastive learning

Lei Li iD, Qiang Zhou, Xinlong Yang, Linye Chen

PLOS One · 2025

DOI: 10.1371/journal.pone.0338546 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Lei Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Ningbo University, College of Science and Technology, Ningbo, Zhejiang, China. Hauptthemen laut MEDLINE: Computer Security, Machine Learning, Computer Communication Networks. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Zhejiang provincial natural science foundation, State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process, State Key Laboratory of Mineral Processing.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advancement of information technology, the Internet, as the core infrastructure for global information exchange, faces increasingly severe security challenges. However, traditional network traffic detection methods typically focus solely on the local features of traffic, failing to comprehensively consider the global relationships between traffic flows. This limitation results in poor detection performance against multi-flow coordinated attacks. Additionally, the inherent imbalance in real-world network traffic data significantly hampers the performance of most models in practical scenarios. To address these issues, this paper proposes a network traffic detection method based on data interpolation and contrastive learning (TICL). The method employs data interpolation techniques to generate negative samples, effectively mitigating the data imbalance problem in real-world scenarios. Furthermore, to enhance the model’s generalization capability, contrastive learning is introduced to capture the differences between positive and negative samples, thereby improving detection performance. Experimental results on two publicly available real-world datasets demonstrate that TICL significantly outperforms existing intrusion detection methods in large-scale data scenarios, showcasing its strong potential for practical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer SecurityMachine LearningComputer Communication NetworksAlgorithmsHumansInternet

Autor:innen und Institutionen

  • Ningbo University, College of Science and Technology, Ningbo, Zhejiang, China.

ORCID-Profile: Lei Li

Förderung

  • Zhejiang provincial natural science foundation
  • State Key Laboratory of Intelligent Optimized Manufacturing in Mining & Metallurgy Process
  • State Key Laboratory of Mineral Processing

Zitieren

APA

Li, L., Zhou, Q., Yang, X., & Chen, L. (2025). Enhancing network traffic detection via interpolation augmentation and contrastive learning. PLOS One. https://doi.org/10.1371/journal.pone.0338546

Vancouver

Li L, Zhou Q, Yang X, Chen L. Enhancing network traffic detection via interpolation augmentation and contrastive learning. PLOS One. 2025. doi:10.1371/journal.pone.0338546

BibTeX
@article{Li2025,
  author = {Li, Lei and Zhou, Qiang and Yang, Xinlong and Chen, Linye},
  title = {Enhancing network traffic detection via interpolation augmentation and contrastive learning},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0338546}
}
Kostenlos starten →