To achieve new applications for 5G communications, physical layer security has recently drawn significant attention. In a wiretap channel system, our goal is to minimize information leakage to an eavesdropper while maximizing the performance of transmission to the desired or legitimate receiver. Complicated systems or channel models make it difficult to design secrecy systems based on the information theory. In this paper, we propose a deep learning-based transceiver design for secrecy systems as an alternative. Specifically, we modify the loss function design of a variational autoencoder, which is a special type of neural network, making it possible to provide both robust data transmission and security in an unsupervised fashion. We further investigate the impact of an imperfect channel state information and use simulation results to prove that our approach can outperform the existing learning-based methods.
To achieve new applications for 5G communications, physical layer security has recently drawn significant attention. In a wiretap channel system, our goal is to minimize information leakage to an eavesdropper while maximizing the performance of transmission to the desired or legitimate receiver. Complicated systems or channel models make it difficult to design secrecy systems based on the information theory. In this paper, we propose a deep learning-based transceiver design for secrecy systems as an alternative. Specifically, we modify the loss function design of a variational autoencoder, which is a special type of neural network, making it possible to provide both robust data transmission and security in an unsupervised fashion. We further investigate the impact of an imperfect channel state information and use simulation results to prove that our approach can outperform the existing learning-based methods.
As one of the indoor communication technologies, visible light communication (VLC) has drawn great attention for its advantages such as ultra-wide unlicensed spectrum, power saving and low complexity. The nature of the visible light propagation is an open channel, which is vulnerable to wiretapping. This paper investigates a secure VLC mechanism enabled by multiple light fixtures acting as friendly jammers. The goal of the friendly jammers is to diminish the capability of the eavesdropper to infer the undisclosed information, on the premise of causing minimal impact on the legitimate receiver. For this reason, an algorithm based on reinforcement learning is proposed to dynamically optimize the friendly jamming policy in realistic nonstationary environments. In order to resolve the difficult problem of the dimensional curse and to effectively represent the continuous state and action spaces, an algorithm based on deep reinforcement learning is devised, which utilizes deep convolutional neural networks to accelerate the convergence rate of the learning process. A differentiable neural dictionary is introduced to make full use of the experiences in similar anti-eavesdropping scenarios to improve the learning capability. Simulation results demonstrate that, the proposed schemes can achieve a higher secrecy rate and a lower bit error rate than some state-of-the-art schemes.
Wireless communications are particularly vulnerable to eavesdropping attacks due to their broadcast nature. To effectively deal with eavesdroppers, existing security techniques usually require accurate channel state information (CSI), e.g., for friendly jamming (FJ), and/or additional computing resources at transceivers, e.g., cryptography-based solutions, which unfortunately may not be feasible in practice. This challenge is even more acute in low-end IoT devices. We thus introduce a novel deep learning-based FJ framework that can effectively defeat eavesdropping attacks with imperfect CSI and even without CSI of legitimate channels. In particular, we first develop an autoencoder-based communication architecture with FJ, namely, AEFJ, to jointly maximize the secrecy rate and minimize the block error rate (BLER) at the receiver without requiring perfect CSI of the legitimate channels. In addition, to deal with the case without CSI, we leverage the mutual information neural estimation (MINE) concept and design a MINE-based FJ scheme that can achieve comparable security performance to the conventional FJ methods that require perfect CSI. Extensive simulations in a multiple-input-multiple-output (MIMO) system demonstrate that our proposed solution can effectively deal with eavesdropping attacks in various settings. Moreover, the proposed framework can seamlessly integrate MIMO security and detection tasks into a unified end-to-end learning process. This integrated approach can significantly maximize the throughput and minimize the BLER, offering a good solution for enhancing communication security in wireless communication systems.
5G is expected to serve completely heterogeneous scenarios where devices with low or high software and hardware complexity will coexist. This entails a security challenge because low complexity devices such as IoT sensors must still have secrecy in their communications. This project proposes tools to maximize the secrecy rate in a scenario with legitimate users and eavesdroppers considering: i) the limitation that low complexity users have in computational power and ii) the eavesdroppers? unwillingness to provide their channel state information to the base station. The tools have been designed based on the physical layer security field and solve the resource allocation from two different approaches that are suitable in different use cases: i) using convex optimization theory or ii) using classification neural networks. Results show that, while the convex approach provides the best secrecy performance, the learning approach is a good alternative for dynamic scenarios or when wanting to save transmitting power.
To avoid the non-convex and complicated secrecy rate optimization in the multiple-input and multiple-output (MIMO) system, deep learning (DL) is introduced in the secure precoder design recently. However, existing works neglect the eavesdropper with learning capacity, which is constructed by neural networks (NNs) and capable of enhancing its receiver NN according to the optimal secure transmitter. In this letter, we propose an adversarial learning-based secure autoprecoder (ASAP) for the MIMO wiretap channels, where the modulation and the precoder are jointly optimized and adversarially trained with the eavesdropping receiver. Numerical results verify the convergence of the ASAP method, which enables an optimal trade-off between the information secrecy and reliability. Moreover, joint optimization is especially important against the evolved eavesdropper.
Physical-layer secret key generation (PSKG) has emerged as a promising technique for enhancing wireless security in Internet of Things (IoT) networks by exploiting the reciprocity of uplink and downlink channels. However, in time-division duplex (TDD) systems, hardware impairments and channel noise disrupt channel reciprocity, degrading key generation performance. To overcome these challenges, this paper introduces a deep learning–enhanced PSKG framework that effectively mitigates channel discrepancies and improves key generation reliability under imperfect channel state information (CSI). Specifically, a two-dimensional convolutional neural network–based autoencoder (2D CNN–AE) with a spatial self-attention (SSA) mechanism is developed to efficiently extract and learn channel reciprocity features in time-division duplex (TDD)-based fifth-generation (5G) networks. Additionally, a quantile-based quantization scheme is proposed to enhance key randomness and entropy, thereby strengthening security and resilience against potential threats. To facilitate comprehensive performance evaluation, a wiretap channel dataset is generated in accordance with 5G standards, encompassing diverse propagation conditions and including both legitimate users and an eavesdropper. Extensive simulation results demonstrate that the proposed 2D CNN–AE–SSA-based PSKG framework significantly reduces the key disagreement ratio (KDR), enhances key randomness, and maintains low computational complexity. These findings establish the proposed method as a robust and practical solution for securing wireless communications in resource-constrained IoT environments.
Location information has been shown to be useful for a wide variety of applications in wireless networks, while its role in physical layer security has so far drawn little attention. In this work, we propose a new location-based secure transmission scheme for wiretap channels, where the accurate locations of the sources, destinations and any other authorized transceivers are known, but only an estimate of the eavesdropper's location is available. We outline how such an estimate of the eavesdropper's location can still allow for quantitative assessment of key security metrics. To provide focus, we describe how optimization of the effective secrecy throughput of a relay wiretap channel is obtained in our scheme, and investigate in detail the impact of the location uncertainty on the system performance. The work reported here provides insights into the design of new location-based physical layer security schemes in which the only information available on an eavesdropper is a noisy estimate of her location.