EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Polarization-Regularized Adversarial Pruning for Efficient Radio Frequency Fingerprint Identification on IoT Devices

Caidan Zhao iD, Haoliang Jiang, Jinhui Yu, Zepeng Meng, Xuhao He

Sensors · 23.03.2026 · 26 (6) · 2005

DOI: 10.3390/s26062005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 23.03.2026. Verfasst von Caidan Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics, Xiamen University, Xiamen 361102, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Radio frequency fingerprint identification (RFFI) based on physical-layer characteristics provides a reliable solution for secure authentication of Internet of Things (IoT) devices. Deep neural networks have demonstrated strong capability in improving RFFI performance; however, their high computational complexity and large parameter size pose significant challenges for deployment on resource-constrained edge devices. In RFFI tasks, existing pruning methods often lack effective performance recovery strategies, which leads to noticeable degradation in identification accuracy after pruning. To address this issue, this paper proposes a pruning method based on adversarial learning and polarization regularization. Polarization regularization is applied to learnable soft masks to effectively distinguish channels to be pruned from those to be retained. In addition, an adversarial learning-based performance recovery strategy is introduced to align the output feature distributions between the baseline network and the pruning network, thereby improving identification accuracy after pruning. Experimental results on multiple RFFI datasets demonstrate that the proposed method can effectively prune ResNet18 and VGG16, achieving substantial reductions in model complexity with only minor losses in identification performance.

Schlagwörter

Stichwörter der Autor:innen

adversarial learningmodel compressionpolarization regularizationpruningradio frequency fingerprint

Autor:innen und Institutionen

  • Department of Informatics, Xiamen University, Xiamen 361102, China.

ORCID-Profile: Caidan Zhao

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China
  • Fundamental Research Funds for the Central Universities
  • National Key R&D Program of China

Zitieren

APA

Zhao, C., Jiang, H., Yu, J., Meng, Z., & He, X. (2026). Polarization-Regularized Adversarial Pruning for Efficient Radio Frequency Fingerprint Identification on IoT Devices. Sensors, 26(6), 2005. https://doi.org/10.3390/s26062005

Vancouver

Zhao C, Jiang H, Yu J, Meng Z, He X. Polarization-Regularized Adversarial Pruning for Efficient Radio Frequency Fingerprint Identification on IoT Devices. Sensors. 2026;26(6):2005. doi:10.3390/s26062005

BibTeX
@article{Zhao2026,
  author = {Zhao, Caidan and Jiang, Haoliang and Yu, Jinhui and Meng, Zepeng and He, Xuhao},
  title = {Polarization-Regularized Adversarial Pruning for Efficient Radio Frequency Fingerprint Identification on IoT Devices},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {2005},
  doi = {10.3390/s26062005}
}
Kostenlos starten →