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

arXiv:2110.07121 · IEEE Wireless Communications Letters

Secure Precoding in MIMO-NOMA: A Deep Learning Approach

Jordan Pauls, Mojtaba Vaezi

Published Oct 15, 2021• 13 citations
arXivHTMLPDF

Abstract

A novel signaling design for secure transmission over two-user multiple-input multiple-output non-orthogonal multiple access channel using deep neural networks (DNNs) is proposed. The goal of the DNN is to form the covariance matrix of users’ signals such that the message of each user is transmitted reliably while being confidential from its counterpart. The proposed DNN linearly precodes each user’s signal before superimposing them and achieves near-optimal performance with significantly lower run time. Simulation results show that the proposed models reach about 98% of the secrecy capacity rates. The spectral efficiency of the DNN precoder is much higher than that of existing analytical linear precoders,–e.g., generalized singular value decomposition–and its on-the-fly complexity is several times less than the existing iterative methods.

DOI
10.1109/lwc.2021.3120594

Related papers

Secure Transmission in MIMO-NOMA Networks

Yue Qi, Mojtaba Vaezi

This letter focuses on the physical layer security over two-user multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) networks. A linear precoding technique is designed to ensure the confidentiality of the message of each user from its counterpart. This technique first splits the base station power between the two users and, based on that, decomposes the secure MIMO-NOMA channel into two MIMO wiretap channels, and designs the transmit covariance matrix for each channel separately. The proposed method substantially enlarges the secrecy rate compared to existing linear precoding methods and strikes a balance between performance and computation cost. Simulation results verify the effectiveness of the proposed method.

arXiv:2008.05923•IEEE Communications Letters•Aug 17, 2020•37 citations

Deep Learning Based Precoding for the MIMO Gaussian Wiretap Channel

Xinliang Zhang, Mojtaba Vaezi

A novel precoding method based on supervised deep neural networks is introduced for the multiple-input multiple-output Gaussian wiretap channel. The proposed deep learning (DL)-based precoding learns the input covariance matrix through offline training over a large set of input channels and their corresponding covariance matrices for efficient, reliable, and secure transmission of information. Furthermore, by spending time in offline training, this method remarkably reduces the computation complexity in real-time applications. Compared to traditional precoding methods, the proposed DL-based precoding is significantly faster and reaches near-capacity secrecy rates. DL based precoding is also more robust than transitional precoding approaches to the number of antennas at the eavesdropper. This new approach to precoding is promising in applications in which delay and complexity are critical.

arXiv:1909.07963•IEEE Globecom Workshops (GC Wkshps)•Dec 1, 2019•28 citations

Deep Neural Network-Based Precoder for Fairness Aware Secure NOMA Scheme

Jin-Young Lee, Sangseok Yun, Il‐Min Kim +1 more

This work proposes an artificial noise (AN)-aided secure multiple-input single-output non-orthogonal multiple access (NOMA) scheme. In the design of the proposed scheme, we consider fairness that all the users have higher secrecy rates as compared to those given by a competing orthogonal multiple access (OMA) scheme. Despite its importance, the fairness aware design has remained rarely touched since it is mathematically intractable. This work shows that this problem can be efficiently solved by utilizing a deep neural network as the precoder for the information and AN signals even without resorting to some assumptions such as a large antenna array and/or a high signal-to-noise ratio. We will also propose an adaptive mode that switches the access protocol from the OMA scheme to the NOMA scheme only when the fairness is met. Performance of the proposed secure NOMA scheme will be extensively evaluated and compared with existing NOMA and OMA schemes. The comparisons clearly show that the sum secrecy rate can be significantly improved while guaranteeing the fairness, which however cannot be achieved with the existing NOMA scheme.

IEEE Transactions on Vehicular Technology•Feb 24, 2022•2 citations

Novel Signaling Design for MIMO-NOMA Against External and Internal Eavesdroppers

Yue Qi, Mojtaba Vaezi, Wonjae Shin

Secure communication over two related multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) networks is investigated. Both networks consist of two legitimate (internal) users and an eavesdropper (external user). In one network, in addition to the external eavesdropper, one of the internal users is also seen as an eavesdropper to the other internal user, resulting in layered confidentiality. The secrecy capacity expressions of these networks are composed of nonconvex functions of transmit covariance matrices, which makes it intractable to find optimal transmit covariance matrices. To overcome this challenge, we form a weighted sum-rate maximization problem for each network and apply the block successive maximization method. This method updates the primal variable blocks successively by maximizing local lower-bounds of the original problem, followed by an update for the dual variable in a closed form. The solutions for these problems design covariance matrices corresponding to the transmitted messages such that they are transmitted securely and reliably. Numerical results illustrate the efficacy of the proposed signaling design for both MIMO-NOMA networks.

IEEE International Conference on Communications workshops•May 16, 2022•0 citations

Deep Neural Network Based Precoding for Wiretap Channels With Finite Alphabet Inputs

Mücahit Gümüş, Tolga M. Duman

We consider secure transmission over multi-input multi-output multi-antenna eavesdropper (MIMOME) wiretap channels with finite alphabet inputs. We use a linear precoder to maximize the secrecy rate, which benefits from the generalized singular value decomposition to obtain independent streams and exploits the function approximation abilities of deep neural networks (DNNs) for solving the required power allocation problem. It is demonstrated that the DNN learns the optimal power allocation without any performance degradation compared to the conventional technique with a significant reduction in complexity.

IEEE Wireless Communications Letters•Apr 28, 2021•5 citations

Joint Precoding Optimization for Secure Transmission in Downlink MISO-NOMA Networks

Dongdong Li, Nan Zhao, Yunfei Chen +3 more

Non-orthogonal multiple access (NOMA) is a prospective technology for radio resource constrained future mobile networks. However, NOMA users far from base station (BS) tend to be more susceptible to eavesdropping because they are allocated more transmit power. In this paper, we aim to jointly optimize the precoding vectors at BS to ensure the legitimate security in a downlink multiple-input single-output (MISO) NOMA network. In the proposed scheme, we can maximize the sum secrecy rate by joint precoding optimization. Owing to its non-convexity, the problem is converted into a convex one, which is solved by a second-order cone programming based iterative algorithm. Simulation results are presented to demonstrate that the proposed schemes can improve the security performance for MISO NOMA systems effectively.

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)•Sep 1, 2019•2 citations
A novel signaling design for secure transmission over two-user multiple-input multiple-output non-orthogonal multiple access channel using deep neural networks (DNNs) is proposed. The goal of the DNN is to form the covariance matrix of users’ signals such that the message of each user is transmitted reliably while being confidential from its counterpart. The proposed DNN linearly precodes each user’s signal before superimposing them and achieves near-optimal performance with significantly lower run time. Simulation results show that the proposed models reach about 98% of the secrecy capacity rates. The spectral efficiency of the DNN precoder is much higher than that of existing analytical linear precoders,–e.g., generalized singular value decomposition–and its on-the-fly complexity is several times less than the existing iterative methods.
This letter focuses on the physical layer security over two-user multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) networks. A linear precoding technique is designed to ensure the confidentiality of the message of each user from its counterpart. This technique first splits the base station power between the two users and, based on that, decomposes the secure MIMO-NOMA channel into two MIMO wiretap channels, and designs the transmit covariance matrix for each channel separately. The proposed method substantially enlarges the secrecy rate compared to existing linear precoding methods and strikes a balance between performance and computation cost. Simulation results verify the effectiveness of the proposed method.
A novel precoding method based on supervised deep neural networks is introduced for the multiple-input multiple-output Gaussian wiretap channel. The proposed deep learning (DL)-based precoding learns the input covariance matrix through offline training over a large set of input channels and their corresponding covariance matrices for efficient, reliable, and secure transmission of information. Furthermore, by spending time in offline training, this method remarkably reduces the computation complexity in real-time applications. Compared to traditional precoding methods, the proposed DL-based precoding is significantly faster and reaches near-capacity secrecy rates. DL based precoding is also more robust than transitional precoding approaches to the number of antennas at the eavesdropper. This new approach to precoding is promising in applications in which delay and complexity are critical.
This work proposes an artificial noise (AN)-aided secure multiple-input single-output non-orthogonal multiple access (NOMA) scheme. In the design of the proposed scheme, we consider fairness that all the users have higher secrecy rates as compared to those given by a competing orthogonal multiple access (OMA) scheme. Despite its importance, the fairness aware design has remained rarely touched since it is mathematically intractable. This work shows that this problem can be efficiently solved by utilizing a deep neural network as the precoder for the information and AN signals even without resorting to some assumptions such as a large antenna array and/or a high signal-to-noise ratio. We will also propose an adaptive mode that switches the access protocol from the OMA scheme to the NOMA scheme only when the fairness is met. Performance of the proposed secure NOMA scheme will be extensively evaluated and compared with existing NOMA and OMA schemes. The comparisons clearly show that the sum secrecy rate can be significantly improved while guaranteeing the fairness, which however cannot be achieved with the existing NOMA scheme.
Secure communication over two related multiple-input multiple-output (MIMO) non-orthogonal multiple access (NOMA) networks is investigated. Both networks consist of two legitimate (internal) users and an eavesdropper (external user). In one network, in addition to the external eavesdropper, one of the internal users is also seen as an eavesdropper to the other internal user, resulting in layered confidentiality. The secrecy capacity expressions of these networks are composed of nonconvex functions of transmit covariance matrices, which makes it intractable to find optimal transmit covariance matrices. To overcome this challenge, we form a weighted sum-rate maximization problem for each network and apply the block successive maximization method. This method updates the primal variable blocks successively by maximizing local lower-bounds of the original problem, followed by an update for the dual variable in a closed form. The solutions for these problems design covariance matrices corresponding to the transmitted messages such that they are transmitted securely and reliably. Numerical results illustrate the efficacy of the proposed signaling design for both MIMO-NOMA networks.
We consider secure transmission over multi-input multi-output multi-antenna eavesdropper (MIMOME) wiretap channels with finite alphabet inputs. We use a linear precoder to maximize the secrecy rate, which benefits from the generalized singular value decomposition to obtain independent streams and exploits the function approximation abilities of deep neural networks (DNNs) for solving the required power allocation problem. It is demonstrated that the DNN learns the optimal power allocation without any performance degradation compared to the conventional technique with a significant reduction in complexity.
Non-orthogonal multiple access (NOMA) is a prospective technology for radio resource constrained future mobile networks. However, NOMA users far from base station (BS) tend to be more susceptible to eavesdropping because they are allocated more transmit power. In this paper, we aim to jointly optimize the precoding vectors at BS to ensure the legitimate security in a downlink multiple-input single-output (MISO) NOMA network. In the proposed scheme, we can maximize the sum secrecy rate by joint precoding optimization. Owing to its non-convexity, the problem is converted into a convex one, which is solved by a second-order cone programming based iterative algorithm. Simulation results are presented to demonstrate that the proposed schemes can improve the security performance for MISO NOMA systems effectively.