EUVIMEDEUVIMED entdecken
Crossref

Scalable-Predictive Beamforming for Integrated Sensing and Covert Communications: A Recurrent Graph Neural Network Approach

Xuemeng Liu, Chang Liu, Wei Xiang, Weijie Yuan, Yonghui Li, Branka Vucetic

IEEE Transactions on Communications · 2026 · 74 · 4742-4757

DOI: 10.1109/tcomm.2026.3658406 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2026. Verfasst von Xuemeng Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: La Trobe University Start-up Package, Australian Research Council’s Discovery Project, Australian Research Council Discovery Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigates a general integrated sensing and covert communication (ISCC) system, where a base station (BS) transmits signals to covert users (CUs) while simultaneously sensing a dynamic target that acts as a warden (WA), maliciously attempting to eavesdrop on the covert communication. An essential task in realizing ISCC is the beamforming design, which however, is complicated by the dynamic nature of both the WA and the CUs in practice, i.e., (i) the rapid movement of the WA and (ii) the time-varying number of CUs. To address these challenges, in this paper, we develop a versatile recurrent graph neural network (RGNN)-based beamforming design framework, where the penalty method is first employed to transform the constrained optimization problem into an unconstrained one, and then an RGNN is customized to effectively output the beamforming vectors. Through implicitly learning features from the historical warden detection channels and the instantaneous channel state information among CUs and BS, the proposed approach could predict the next-time-slot beamforming matrix while accommodating a scalable number of CUs, thus eliminating repeated WA channel estimation and re-optimization when handling dynamic scenarios. Moreover, a convolutional long short-term memory (CLSTM)-augmented message passing GNN (CL-MPGNN) is developed to realize the RGNN framework. In particular, a CLSTM module is first adopted to exploit the spatial-temporal features from the input to facilitate an effective predictive beamforming. Then, a set of message-passing layers is employed to guarantee the scalability of the beamforming design. Simulations verify the effectiveness of the proposed algorithm in terms of the covert communication performance, the covert communication-sensing tradeoff, and the generalizability, respectively.

Förderung

  • La Trobe University Start-up Package
  • Australian Research Council’s Discovery Project
  • Australian Research Council Discovery Project

Zitieren

APA

Liu, X., Liu, C., Xiang, W., Yuan, W., Li, Y., & Vucetic, B. (2026). Scalable-Predictive Beamforming for Integrated Sensing and Covert Communications: A Recurrent Graph Neural Network Approach. IEEE Transactions on Communications, 74, 4742-4757. https://doi.org/10.1109/tcomm.2026.3658406

Vancouver

Liu X, Liu C, Xiang W, Yuan W, Li Y, Vucetic B. Scalable-Predictive Beamforming for Integrated Sensing and Covert Communications: A Recurrent Graph Neural Network Approach. IEEE Transactions on Communications. 2026;74:4742-4757. doi:10.1109/tcomm.2026.3658406

BibTeX
@article{Liu2026,
  author = {Liu, Xuemeng and Liu, Chang and Xiang, Wei and Yuan, Weijie and Li, Yonghui and Vucetic, Branka},
  title = {Scalable-Predictive Beamforming for Integrated Sensing and Covert Communications: A Recurrent Graph Neural Network Approach},
  journal = {IEEE Transactions on Communications},
  year = {2026},
  volume = {74},
  pages = {4742--4757},
  doi = {10.1109/tcomm.2026.3658406}
}
Kostenlos starten →