Home > Research > Publications & Outputs > Deep Reinforcement Learning Based Uplink Securi...

Associated organisational unit

Electronic data

  • IoTJ_Final

    Accepted author manuscript, 1.11 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers. / Qin, Xintong; Song, Zhengyu; Wang, Jun et al.
In: IEEE Internet of Things Journal, Vol. 11, No. 17, 30.09.2024, p. 28050-28063.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Qin, X, Song, Z, Wang, J, Du, S, Gao, J, Yu, W & Sun, X 2024, 'Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers', IEEE Internet of Things Journal, vol. 11, no. 17, pp. 28050-28063. https://doi.org/10.1109/jiot.2024.3416334

APA

Vancouver

Qin X, Song Z, Wang J, Du S, Gao J, Yu W et al. Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers. IEEE Internet of Things Journal. 2024 Sept 30;11(17):28050-28063. Epub 2024 Jun 18. doi: 10.1109/jiot.2024.3416334

Author

Qin, Xintong ; Song, Zhengyu ; Wang, Jun et al. / Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers. In: IEEE Internet of Things Journal. 2024 ; Vol. 11, No. 17. pp. 28050-28063.

Bibtex

@article{8514fd30d9224f66b26c219e4beba5b5,
title = "Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers",
abstract = "This article investigates the simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted nonorthogonal multiple access (NOMA) systems with one cooperative jammer and dual eavesdroppers. To guarantee the uplink secure transmission, we maximize the sum secrecy rate under both the perfect and imperfect channel state information (CSI) by jointly optimizing the channel allocation, transmit power, and coefficient matrices. For the problem with perfect CSI, a deep reinforcement learning algorithm is proposed based on the deep deterministic policy gradient (DDPG) framework. Then, by introducing the arbitrary distorted noise to the state space, the proposed algorithm is extended to solve the problem under imperfect CSI without causing additional computational complexity. Simulation results illustrate that: 1) the symmetry of STAR-RIS results in severe information leakage and the sum secrecy rate further degrades when the dual eavesdroppers collaborate with each other; 2) the STAR-RIS with independent phase shift can achieve higher sum secrecy rate than that with coupled phase shift, while the performance gap is trivial when there are fewer STAR-RIS elements; and 3) our proposed algorithm can compensate for the impacts of the imperfect CSI, and the sum secrecy rate decreases with the increase of CSI uncertainty.",
keywords = "Deep reinforcement learning (DRL), physical layer security (PLS), resource allocation, simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)",
author = "Xintong Qin and Zhengyu Song and Jun Wang and Shengyu Du and Jiazi Gao and Wenjuan Yu and Xin Sun",
year = "2024",
month = sep,
day = "30",
doi = "10.1109/jiot.2024.3416334",
language = "English",
volume = "11",
pages = "28050--28063",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",
number = "17",

}

RIS

TY - JOUR

T1 - Deep Reinforcement Learning Based Uplink Security Enhancement for STAR-RIS-Assisted NOMA Systems With Dual Eavesdroppers

AU - Qin, Xintong

AU - Song, Zhengyu

AU - Wang, Jun

AU - Du, Shengyu

AU - Gao, Jiazi

AU - Yu, Wenjuan

AU - Sun, Xin

PY - 2024/9/30

Y1 - 2024/9/30

N2 - This article investigates the simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted nonorthogonal multiple access (NOMA) systems with one cooperative jammer and dual eavesdroppers. To guarantee the uplink secure transmission, we maximize the sum secrecy rate under both the perfect and imperfect channel state information (CSI) by jointly optimizing the channel allocation, transmit power, and coefficient matrices. For the problem with perfect CSI, a deep reinforcement learning algorithm is proposed based on the deep deterministic policy gradient (DDPG) framework. Then, by introducing the arbitrary distorted noise to the state space, the proposed algorithm is extended to solve the problem under imperfect CSI without causing additional computational complexity. Simulation results illustrate that: 1) the symmetry of STAR-RIS results in severe information leakage and the sum secrecy rate further degrades when the dual eavesdroppers collaborate with each other; 2) the STAR-RIS with independent phase shift can achieve higher sum secrecy rate than that with coupled phase shift, while the performance gap is trivial when there are fewer STAR-RIS elements; and 3) our proposed algorithm can compensate for the impacts of the imperfect CSI, and the sum secrecy rate decreases with the increase of CSI uncertainty.

AB - This article investigates the simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted nonorthogonal multiple access (NOMA) systems with one cooperative jammer and dual eavesdroppers. To guarantee the uplink secure transmission, we maximize the sum secrecy rate under both the perfect and imperfect channel state information (CSI) by jointly optimizing the channel allocation, transmit power, and coefficient matrices. For the problem with perfect CSI, a deep reinforcement learning algorithm is proposed based on the deep deterministic policy gradient (DDPG) framework. Then, by introducing the arbitrary distorted noise to the state space, the proposed algorithm is extended to solve the problem under imperfect CSI without causing additional computational complexity. Simulation results illustrate that: 1) the symmetry of STAR-RIS results in severe information leakage and the sum secrecy rate further degrades when the dual eavesdroppers collaborate with each other; 2) the STAR-RIS with independent phase shift can achieve higher sum secrecy rate than that with coupled phase shift, while the performance gap is trivial when there are fewer STAR-RIS elements; and 3) our proposed algorithm can compensate for the impacts of the imperfect CSI, and the sum secrecy rate decreases with the increase of CSI uncertainty.

KW - Deep reinforcement learning (DRL)

KW - physical layer security (PLS)

KW - resource allocation

KW - simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)

U2 - 10.1109/jiot.2024.3416334

DO - 10.1109/jiot.2024.3416334

M3 - Journal article

VL - 11

SP - 28050

EP - 28063

JO - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

IS - 17

ER -