EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FD-IDS: Federated Learning with Knowledge Distillation for Intrusion Detection in Non-IID IoT Environments

Haonan Peng iD, Chunming Wu, Yanfeng Xiao

Sensors · 10.07.2025 · 25 (14) · 4309

DOI: 10.3390/s25144309 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.07.2025. Verfasst von Haonan Peng und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China. Die Arbeit wurde bisher 54-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: "Pioneer" and "Leading Goose" R&D Program of Zhejiang, “Pioneer” and “Leading Goose” R&D Program of Zhejiang.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid advancement of Internet of Things (IoT) technology, intrusion detection systems (IDSs) have become pivotal in ensuring network security. However, the data produced by IoT devices is typically sensitive and tends to display non-independent and identically distributed (Non-IID) properties. These factors impose significant limitations on the application of traditional centralized learning. In response to these issues, this study introduces a novel IDS framework grounded in federated learning and knowledge distillation (KD), termed FD-IDS. The proposed FD-IDS aims to tackle issues related to safeguarding data privacy and distributed heterogeneity. FD-IDS employs mutual information for feature selection to enhance training efficiency. For Non-IID data scenarios, the system combines a proximal term with KD. The proximal term restricts the deviation between local and global models, while KD utilizes the global model to steer the training process of local models. Together, these mechanisms effectively alleviate the problem of model drift. Experiments conducted on both the Edge-IIoT and N-BaIoT datasets demonstrate that FD-IDS achieves promising detection performance across multiple evaluation metrics.

Schlagwörter

Stichwörter der Autor:innen

IoT securityNon-IIDfeature selectionfederated learningintrusion detectionknowledge distillation

Autor:innen und Institutionen

  • College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China.
  • China Mobile Group Huzhou Co., Ltd., Huzhou 313098, China.

ORCID-Profile: Haonan Peng

Förderung

  • "Pioneer" and "Leading Goose" R&D Program of Zhejiang
  • “Pioneer” and “Leading Goose” R&D Program of Zhejiang

Zitieren

APA

Peng, H., Wu, C., & Xiao, Y. (2025). FD-IDS: Federated Learning with Knowledge Distillation for Intrusion Detection in Non-IID IoT Environments. Sensors, 25(14), 4309. https://doi.org/10.3390/s25144309

Vancouver

Peng H, Wu C, Xiao Y. FD-IDS: Federated Learning with Knowledge Distillation for Intrusion Detection in Non-IID IoT Environments. Sensors. 2025;25(14):4309. doi:10.3390/s25144309

BibTeX
@article{Peng2025,
  author = {Peng, Haonan and Wu, Chunming and Xiao, Yanfeng},
  title = {FD-IDS: Federated Learning with Knowledge Distillation for Intrusion Detection in Non-IID IoT Environments},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {14},
  pages = {4309},
  doi = {10.3390/s25144309}
}
Kostenlos starten →