Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Globecom

Deep Reinforcement Learning for Enhancing the Secrecy of a MU-MISO UOWC Network

Elmehdi Illi, Emna Baccour, Marwa Qaraqe, Mounir Hamdi

Published Dec 4, 2023• 1 citation
Publisher

Abstract

In this paper, we propose a Deep Reinforcement Learning (DRL) framework to optimize the secrecy performance of a Multi-User (MU)-Multiple-Input Single-Output (MISO) Underwater Optical Wireless Communication (UOWC) system. The network consists of several light-emitting diodes connected with various underwater users through optical beams. The legitimate transmission is threatened by several eavesdroppers attempting to overhear the confidential message sent to each user. Thus, digital precoding is employed to cancel the inter-user interference and maximize the per-user secrecy rate and, consequently, the secrecy sum rate (SSR). Leveraging the developed DRL algorithm, the MU-MISO precoding matrix is optimized for enhancing the system's SSR. Numerical results show the superiority of the proposed DRL framework compared to the baseline zero-forcing and random pre coding schemes, even with corrupted CSI at the transmitter due to seawater dynamics and estimation errors.

DOI
10.1109/globecom54140.2023.10437117

Related papers

On the Physical Layer Security of Underwater Optical Wireless Communication Networks

Elmehdi Illi, Marwa Qaraqe

This article deals with the secrecy analysis of an underwater optical wireless communication (UOWC) system operating under the presence of underwater turbulence and geometric path loss. The considered system consists of either a single transmit laser diode (LD) and multiple receive photodetectors (PD), i.e., single-input multiple-output (SIMO), employing maximal-ratio combining (MRC) technique, or a multiple-input single-output (MISO) with multiple LDs and a single PD using the maximal-ratio transmission (MRT) precoding scheme. A tight approximate expression for the average secrecy capacity (ASC)’s lower bound is provided in terms of the key system parameters. Results indicate that the system's secrecy can be enhanced by either increasing the number of receive PDs or the legal node's PDs size compared to the illegitimate one, whereby the ASC can exceed 4 b/s/Hz when the legitimate PD diameter is twice the eavesdropper's one. In addition, narrow beams and low water turbidity levels provide optimal secrecy performance. Finally, a comparative analysis between the SIMO-MRC and MISO-MRT schemes shows that the latter outperforms its former counterpart.

IEEE Journal of Oceanic Engineering•Feb 6, 2024•21 citations

Deep Reinforcement Learning-Enabled Secure Visible Light Communication Against Eavesdropping

Liang Xiao, Geyi Sheng, Sicong Liu +3 more

The inherent broadcast characteristics of the visible light communication (VLC) channel makes VLC downlinks susceptible to unauthorized terminals in many actual VLC scenarios, such as offices and shopping centers. This paper considers a multiple-input-single-output (MISO) VLC scenario with multiple light fixtures acting as the transmitter, a VLC receiver as the legitimate user, and an eavesdropper attempting to intercept the undisclosed information. To improve the confidentiality of VLC links, a physical-layer anti-eavesdropping framework is proposed to obscure the unauthorized eavesdroppers and diminishes their capability of inferring the information through smart beamforming over the MISO VLC wiretap channel. To cope with the intractable problem of finding the theoretically optimal solution of the secrecy rate and utility for the MISO VLC wiretapping channel, a reinforcement learning (RL)-based VLC beamforming control scheme is proposed to achieve the optimal beamforming policy against the eavesdropper. Furthermore, a deep RL-based VLC beamforming control scheme is proposed to handle the curse of dimensionality for both observation space and action space and avoid the quantization error of the RL-based algorithm. Simulation results show that the proposed learning-based VLC beamforming control schemes can significantly decrease the bit error rate of the legitimate receiver and increase the secrecy rate and utility of the anti-eavesdropping MISO VLC system, compared with the benchmark strategy.

IEEE Transactions on Communications•Jul 22, 2019•111 citations

Robust Sum Secrecy Rate Optimization for MISO Systems with Device-to-Device Communication

Weidong Mei, Zhi Chen, Jun Fang

This paper considers a cellular multiple-input single- output (MISO) system overheard by multiple eavesdroppers, in the presence of one pair of device- to-device (D2D) nodes working as an underlay to the cellular network. A novel eavesdropping scenario is studied in this paper, where the eavesdroppers intend to simultaneously overhear the cellular communication as well as the D2D communication. Assuming imperfect channel state information (CSI) at the transmitter, our goal is to design the input covariance matrix of confidential message such that the worst-case sum secrecy rate is maximized, while satisfying the quality of service (QoS) requirement in the D2D communication. Although this worst-case sum secrecy rate maximization (SSRM) problem is non-convex, we show that it can be handled by solving a sequence of semidefinite programming (SDP) problems. Moreover, we give complexity analysis of our proposed optimization method and prove that transmit beamforming is an optimal strategy for the confidential message transmission. Numerical results are presented to verify the efficacy of our proposed method.

IEEE Vehicular Technology Conference•Jun 1, 2017•0 citations

Secrecy Performance of Multi-User MISO VLC Broadcast Channels With Confidential Messages

Mohamed Amine Arfaoui, Ali Ghrayeb, Chadi M. Assi

We study, in this paper, the secrecy performance of a multi-user (MU) multiple-input single-output visible light communication broadcast channel with confidential messages. The underlying system model comprises K +1 nodes: a transmitter (Alice) equipped with N fixtures of LEDs and K spatially dispersed users, each equipped with a single photo-diode. The MU channel is modeled as deterministic and real-valued and assumed to be perfectly known to Alice, since all users are assumed to be active. We consider typical secrecy performance measures, namely, the max-min fairness, the harmonic mean, the proportional fairness, and the weighted fairness. For each performance measure, we derive an achievable secrecy rate for the system as a function of the precoding matrix. As such, we propose algorithms that yield the best precoding matrix for the derived secrecy rates, where we analyze their convergence and computational complexity. In contrast, what has been considered in the literature so far is zero-forcing (ZF) precoding, which is suboptimal. We present several numerical examples through which we demonstrate the substantial improvements in the secrecy performance achieved by the proposed techniques compared with those achieved by the conventional ZF. However, this comes at a slight increase in the complexity of the proposed techniques compared with ZF.

IEEE Transactions on Wireless Communications•Sep 26, 2018•57 citations

DRL-Enhanced Security in RIS-Assisted Systems Simultaneous Against Eavesdropping and Jamming

Abraham Tesfai, Junyu Ma, Z. J. Zhang +3 more

The escalating demand for secure wireless communication, driven by the proliferation of connected devices, has made information security a paramount concern. Traditional encryption methods struggle against eavesdropping and malicious jamming in open wireless channels, necessitating innovative solutions. This paper explores physical layer security, leveraging intrinsic wireless channel properties, enhanced by reconfigurable intelligent surface (RIS). We propose an RIS-assisted multiple-input single-output system to counteract eavesdroppers and jamming threats through an artificial noise (AN) cooperation scheme. AN is injected during legitimate beamforming to bolster transmission security. Jointly optimizing the base station’s precoding vector, AN vector, and RIS reflection coefficients under power, quality, and phase constraints, we formulate a non-convex secrecy rate (SR) maximization problem. Addressing its complexity, we model it as a Markov decision process and develop a deep deterministic policy gradient algorithm within a deep reinforcement learning framework. Simulation results demonstrate the proposed method’s superior performance, reduced complexity, and robustness against multiple eavesdroppers and high-power jamming, underscoring the critical roles of RIS and AN in securing wireless communications. It consistently outperforms traditional algorithms such as alternating optimization with semidefinite programming, offering up to 7% higher SR and achieving nearly 120% SR gains as RIS elements scale from N =4 to N =10.

IEEE/CIC International Conference on Communications in China (ICCC)•Aug 10, 2025•0 citations

Secrecy Outage-Constrained Robust Resource Allocation Design for MU-MISO RSMA Systems

Hao Fu, Suili Feng, Weijun Tang +2 more

In this paper, we study the robust and fair transmission design for a rate splitting multiple access (RSMA)-based multi-user multiple-input single-output (MU-MISO) probabilistic secrecy communication system, where the statistic distribution of estimation errors of eavesdropping channels is available at the transmitter. Our robust resource allocation design aims to maximize the minimum achievable outage constrained (OC) secrecy rate among multiple single-antenna legitimated users (LUs) via optimizing the beamforming vectors and the artificial noise (AN) matrix at the transmitter. To this end, the algorithm design is formulated as a non-convex probabilistic optimization problem which takes into account the maximum transmit power budget. To address the intractability of the optimization problem, the successive convex approximation (SCA) technique and the alternating optimization (AO) approach are exploited to design a suboptimal iterative algorithm for obtaining a locally optimal solution of the considered problem. Simulation results demonstrate that the minimum achievable OC secrecy rate performance of our proposed RSMA-based probabilistic secure transmission system outperforms that of several baseline schemes.

IEEE Globecom Workshops (GC Wkshps)•Dec 1, 2021•2 citations
In this paper, we propose a Deep Reinforcement Learning (DRL) framework to optimize the secrecy performance of a Multi-User (MU)-Multiple-Input Single-Output (MISO) Underwater Optical Wireless Communication (UOWC) system. The network consists of several light-emitting diodes connected with various underwater users through optical beams. The legitimate transmission is threatened by several eavesdroppers attempting to overhear the confidential message sent to each user. Thus, digital precoding is employed to cancel the inter-user interference and maximize the per-user secrecy rate and, consequently, the secrecy sum rate (SSR). Leveraging the developed DRL algorithm, the MU-MISO precoding matrix is optimized for enhancing the system's SSR. Numerical results show the superiority of the proposed DRL framework compared to the baseline zero-forcing and random pre coding schemes, even with corrupted CSI at the transmitter due to seawater dynamics and estimation errors.
This article deals with the secrecy analysis of an underwater optical wireless communication (UOWC) system operating under the presence of underwater turbulence and geometric path loss. The considered system consists of either a single transmit laser diode (LD) and multiple receive photodetectors (PD), i.e., single-input multiple-output (SIMO), employing maximal-ratio combining (MRC) technique, or a multiple-input single-output (MISO) with multiple LDs and a single PD using the maximal-ratio transmission (MRT) precoding scheme. A tight approximate expression for the average secrecy capacity (ASC)’s lower bound is provided in terms of the key system parameters. Results indicate that the system's secrecy can be enhanced by either increasing the number of receive PDs or the legal node's PDs size compared to the illegitimate one, whereby the ASC can exceed 4 b/s/Hz when the legitimate PD diameter is twice the eavesdropper's one. In addition, narrow beams and low water turbidity levels provide optimal secrecy performance. Finally, a comparative analysis between the SIMO-MRC and MISO-MRT schemes shows that the latter outperforms its former counterpart.
The inherent broadcast characteristics of the visible light communication (VLC) channel makes VLC downlinks susceptible to unauthorized terminals in many actual VLC scenarios, such as offices and shopping centers. This paper considers a multiple-input-single-output (MISO) VLC scenario with multiple light fixtures acting as the transmitter, a VLC receiver as the legitimate user, and an eavesdropper attempting to intercept the undisclosed information. To improve the confidentiality of VLC links, a physical-layer anti-eavesdropping framework is proposed to obscure the unauthorized eavesdroppers and diminishes their capability of inferring the information through smart beamforming over the MISO VLC wiretap channel. To cope with the intractable problem of finding the theoretically optimal solution of the secrecy rate and utility for the MISO VLC wiretapping channel, a reinforcement learning (RL)-based VLC beamforming control scheme is proposed to achieve the optimal beamforming policy against the eavesdropper. Furthermore, a deep RL-based VLC beamforming control scheme is proposed to handle the curse of dimensionality for both observation space and action space and avoid the quantization error of the RL-based algorithm. Simulation results show that the proposed learning-based VLC beamforming control schemes can significantly decrease the bit error rate of the legitimate receiver and increase the secrecy rate and utility of the anti-eavesdropping MISO VLC system, compared with the benchmark strategy.
This paper considers a cellular multiple-input single- output (MISO) system overheard by multiple eavesdroppers, in the presence of one pair of device- to-device (D2D) nodes working as an underlay to the cellular network. A novel eavesdropping scenario is studied in this paper, where the eavesdroppers intend to simultaneously overhear the cellular communication as well as the D2D communication. Assuming imperfect channel state information (CSI) at the transmitter, our goal is to design the input covariance matrix of confidential message such that the worst-case sum secrecy rate is maximized, while satisfying the quality of service (QoS) requirement in the D2D communication. Although this worst-case sum secrecy rate maximization (SSRM) problem is non-convex, we show that it can be handled by solving a sequence of semidefinite programming (SDP) problems. Moreover, we give complexity analysis of our proposed optimization method and prove that transmit beamforming is an optimal strategy for the confidential message transmission. Numerical results are presented to verify the efficacy of our proposed method.
We study, in this paper, the secrecy performance of a multi-user (MU) multiple-input single-output visible light communication broadcast channel with confidential messages. The underlying system model comprises K +1 nodes: a transmitter (Alice) equipped with N fixtures of LEDs and K spatially dispersed users, each equipped with a single photo-diode. The MU channel is modeled as deterministic and real-valued and assumed to be perfectly known to Alice, since all users are assumed to be active. We consider typical secrecy performance measures, namely, the max-min fairness, the harmonic mean, the proportional fairness, and the weighted fairness. For each performance measure, we derive an achievable secrecy rate for the system as a function of the precoding matrix. As such, we propose algorithms that yield the best precoding matrix for the derived secrecy rates, where we analyze their convergence and computational complexity. In contrast, what has been considered in the literature so far is zero-forcing (ZF) precoding, which is suboptimal. We present several numerical examples through which we demonstrate the substantial improvements in the secrecy performance achieved by the proposed techniques compared with those achieved by the conventional ZF. However, this comes at a slight increase in the complexity of the proposed techniques compared with ZF.
The escalating demand for secure wireless communication, driven by the proliferation of connected devices, has made information security a paramount concern. Traditional encryption methods struggle against eavesdropping and malicious jamming in open wireless channels, necessitating innovative solutions. This paper explores physical layer security, leveraging intrinsic wireless channel properties, enhanced by reconfigurable intelligent surface (RIS). We propose an RIS-assisted multiple-input single-output system to counteract eavesdroppers and jamming threats through an artificial noise (AN) cooperation scheme. AN is injected during legitimate beamforming to bolster transmission security. Jointly optimizing the base station’s precoding vector, AN vector, and RIS reflection coefficients under power, quality, and phase constraints, we formulate a non-convex secrecy rate (SR) maximization problem. Addressing its complexity, we model it as a Markov decision process and develop a deep deterministic policy gradient algorithm within a deep reinforcement learning framework. Simulation results demonstrate the proposed method’s superior performance, reduced complexity, and robustness against multiple eavesdroppers and high-power jamming, underscoring the critical roles of RIS and AN in securing wireless communications. It consistently outperforms traditional algorithms such as alternating optimization with semidefinite programming, offering up to 7% higher SR and achieving nearly 120% SR gains as RIS elements scale from N =4 to N =10.
In this paper, we study the robust and fair transmission design for a rate splitting multiple access (RSMA)-based multi-user multiple-input single-output (MU-MISO) probabilistic secrecy communication system, where the statistic distribution of estimation errors of eavesdropping channels is available at the transmitter. Our robust resource allocation design aims to maximize the minimum achievable outage constrained (OC) secrecy rate among multiple single-antenna legitimated users (LUs) via optimizing the beamforming vectors and the artificial noise (AN) matrix at the transmitter. To this end, the algorithm design is formulated as a non-convex probabilistic optimization problem which takes into account the maximum transmit power budget. To address the intractability of the optimization problem, the successive convex approximation (SCA) technique and the alternating optimization (AO) approach are exploited to design a suboptimal iterative algorithm for obtaining a locally optimal solution of the considered problem. Simulation results demonstrate that the minimum achievable OC secrecy rate performance of our proposed RSMA-based probabilistic secure transmission system outperforms that of several baseline schemes.