EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A temperature-adaptive logit-standardized knowledge distillation for lightweight network intrusion detection

XiaoFang Dong iD, Kai Yang iD, JingChao Liu, Wen Chen

PLOS One · 02.11.2026 · 21 (11) · e0361860

DOI: 10.1371/journal.pone.0361860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 02.11.2026. Verfasst von XiaoFang Dong und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer, Xijing University, Xi'an, Shaanxi, China. Hauptthemen laut MEDLINE: Computer Communication Networks. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of the Internet has made network attacks increasingly frequent, stealthy, and diverse, posing stringent requirements on the accuracy and latency of network intrusion detection systems (NIDS). Although deep-learning-based NIDS can achieve strong detection performance, their large parameter size and high computational cost hinder deployment on resource-constrained edge devices. To address this limitation, we propose a temperature-adaptive logit-standardized knowledge distillation framework for lightweight network intrusion detection. A high-capacity teacher network first learns discriminative representations from network traffic, and a compact student network is then trained to mimic the teacher under a tailored distillation scheme. During distillation, we apply per-sample Z-score standardization to the logits of both teacher and student models to mitigate scale mismatch and emphasize relative inter-class relationships. Moreover, we adapt the distillation temperature according to sample difficulty and training progress, enabling suitably smoothed soft targets across samples and stages, and jointly optimize the student with hard-label supervision. Experiments on benchmark datasets including NSL-KDD and CIC-IDS2017 demonstrate that the proposed method substantially reduces model complexity while maintaining stable and competitive detection performance. Additional repeated-run, ablation, and lightweight baseline analyses further indicate that the proposed framework achieves a favorable accuracy–complexity trade-off.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computer Communication NetworksTemperatureInternetAlgorithms

Autor:innen und Institutionen

  • School of Computer, Xijing University, Xi'an, Shaanxi, China.
  • Xi'an Key Laboratory of Human-Machine Integration and Control Technology for Intelligent Rehabilitation, School of Computer Science, Xijing University, Xi'an, Shaanxi, China.

ORCID-Profile: XiaoFang Dong, Kai Yang

Zitieren

APA

Dong, X., Yang, K., Liu, J., & Chen, W. (2026). A temperature-adaptive logit-standardized knowledge distillation for lightweight network intrusion detection. PLOS One, 21(11), e0361860. https://doi.org/10.1371/journal.pone.0361860

Vancouver

Dong X, Yang K, Liu J, Chen W. A temperature-adaptive logit-standardized knowledge distillation for lightweight network intrusion detection. PLOS One. 2026;21(11):e0361860. doi:10.1371/journal.pone.0361860

BibTeX
@article{Dong2026,
  author = {Dong, XiaoFang and Yang, Kai and Liu, JingChao and Chen, Wen},
  title = {A temperature-adaptive logit-standardized knowledge distillation for lightweight network intrusion detection},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0361860},
  doi = {10.1371/journal.pone.0361860}
}
Kostenlos starten →