EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Self-Supervised Specific Emitter Identification Method Based on Contrastive Asymmetric Masked Learning

Dong Wang iD, Yonghui Huang iD, Tianshu Cui iD, Yan Zhu

Sensors · 27.06.2025 · 25 (13) · 4023

DOI: 10.3390/s25134023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.06.2025. Verfasst von Dong Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 10019…. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Specific emitter identification (SEI) is a core technology for wireless device security that plays a crucial role in protecting wireless communication systems from various security threats. However, current deep learning-based SEI methods heavily rely on large amounts of labeled data for supervised training, facing challenges in non-cooperative communication scenarios. To address these issues, this paper proposes a novel contrastive asymmetric masked learning-based SEI (CAML-SEI) method, effectively solving the problem of SEI under scarce labeled samples. The proposed method constructs an asymmetric auto-encoder architecture, comprising an encoder network based on channel squeeze-and-excitation residual blocks to capture radio frequency fingerprint (RFF) features embedded in signals, while employing a lightweight single-layer convolutional decoder for masked signal reconstruction. This design promotes the learning of fine-grained local feature representations. To further enhance feature discriminability, a learnable non-linear mapping is introduced to compress high-dimensional encoded features into a compact low-dimensional space, accompanied by a contrastive loss function that simultaneously achieves feature aggregation of positive samples and feature separation of negative samples. Finally, the network is jointly optimized by combining signal reconstruction and feature contrast tasks. Experiments conducted on real-world ADS-B and Wi-Fi datasets demonstrate that the proposed method effectively learns generalized RFF features, and the results show superior performance compared with other SEI methods.

Schlagwörter

Stichwörter der Autor:innen

asymmetric masked auto-encodercontrastive learningself-supervised learningspecific emitter identificationwireless device security

Autor:innen und Institutionen

  • Key Laboratory of Electronics and Information Technology for Space Systems, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China.
  • University of Chinese Academy of Sciences, Beijing 100049, China.
  • China Academy of Aerospace Science and Innovation, Beijing 100080, China.

ORCID-Profile: Dong Wang, Yonghui Huang, Tianshu Cui

Zitieren

APA

Wang, D., Huang, Y., Cui, T., & Zhu, Y. (2025). A Self-Supervised Specific Emitter Identification Method Based on Contrastive Asymmetric Masked Learning. Sensors, 25(13), 4023. https://doi.org/10.3390/s25134023

Vancouver

Wang D, Huang Y, Cui T, Zhu Y. A Self-Supervised Specific Emitter Identification Method Based on Contrastive Asymmetric Masked Learning. Sensors. 2025;25(13):4023. doi:10.3390/s25134023

BibTeX
@article{Wang2025,
  author = {Wang, Dong and Huang, Yonghui and Cui, Tianshu and Zhu, Yan},
  title = {A Self-Supervised Specific Emitter Identification Method Based on Contrastive Asymmetric Masked Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {4023},
  doi = {10.3390/s25134023}
}
Kostenlos starten →