RIS-Aided Physical Layer Security with Imperfect CSI: A Robust Model-Driven Deep Learning Approach
Entropy · 16.04.2026 · 28 (4) · 457
DOI: 10.3390/e28040457 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 16.04.2026. Verfasst von Ruikai Miao und 6 weiteren Autor:innen. Beteiligte Einrichtung: The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hebei Province, China, Postdoctoral Science Foundation of Hebei Province, National Key Laboratory of Wireless Communications Foundation.
Abstract (Originalsprache)
Reconfigurable intelligent surface (RIS) emerges as a promising paradigm and offers a new perspective for physical layer security. In practice, imperfect eavesdropper channel state information (CSI) represents a critical challenge for RIS-aided physical layer security design. To tackle this issue, this paper investigates RIS-aided physical layer security enhancement under imperfect eavesdropper CSI and formulates a robust weighted sum secrecy rate maximization problem. To efficiently solve this problem, a model-driven deep learning approach is proposed. We begin by introducing the gradient descent–ascent algorithm to solve the optimization problem. Then we unfold this algorithm into a gated recurrent unit (GRU)-aided deep unfold network with trainable parameters. The proposed GRU-aided deep unfold network leverages GRU to adaptively generate gradient ascent–descent step sizes. Different from the existing deep unfold network that commonly has a fixed number of iteration, the proposed deep unfold network integrates the sequential learning capability of GRU and enables adaptive iteration adjustment. The simulation results demonstrate that compared to existing non-robust optimization algorithm and traditional deep unfold network with fixed number of iteration, the proposed method exhibits robustness against imperfect CSI and achieves higher weighted sum secrecy rate.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, China.
- National Key Laboratory of Advanced Communication Networks, Shijiazhuang 050081, China.
- North Automatic Control Technology Institute, Taiyuan 030006, China.
ORCID-Profile: Ruikai Miao, Xingjian Li
Förderung
- Natural Science Foundation of Hebei Province, China
- Postdoctoral Science Foundation of Hebei Province
- National Key Laboratory of Wireless Communications Foundation
Zitieren
APA
Miao, R., Song, Z., Li, Y., Li, X., Liu, L., Shao, G., & Wang, B. (2026). RIS-Aided Physical Layer Security with Imperfect CSI: A Robust Model-Driven Deep Learning Approach. Entropy, 28(4), 457. https://doi.org/10.3390/e28040457
Vancouver
Miao R, Song Z, Li Y, Li X, Liu L, Shao G, et al. RIS-Aided Physical Layer Security with Imperfect CSI: A Robust Model-Driven Deep Learning Approach. Entropy. 2026;28(4):457. doi:10.3390/e28040457
BibTeX
@article{Miao2026,
author = {Miao, Ruikai and Song, Zhiqun and Li, Yong and Li, Xingjian and Liu, Lizhe and Shao, Guoyuan and Wang, Bin},
title = {RIS-Aided Physical Layer Security with Imperfect CSI: A Robust Model-Driven Deep Learning Approach},
journal = {Entropy},
year = {2026},
volume = {28},
number = {4},
pages = {457},
doi = {10.3390/e28040457}
}
EUVIMED