Leveraging the spatial sensitivity characteristics of millimeter-wave technology to integrate communication and sensing presents a highly promising approach for industrial manufacturing systems. This paper proposes a novel integrated sensing and communication method for detecting the physical spatial location of industrial wireless sensor nodes based on beam pattern trajectories. In particular, to handle the incomplete phenomenon of beam patterns during communication, a beam pattern trajectory fusion method is presented by reconstructing incomplete sector-level sweep (SLS) SNR data to enhance the feature robustness. To address the challenge of small sample size, a Siamese network architecture is designed, leveraging dual-branch feature embeddings to detect sub-centimeter displacements and angular deviations. Experimental evaluations on commercial Talon AD7200 devices achieve over 95% accuracy across diverse distances (1–6 m), hardware variations and temporal conditions, while reducing training data requirements by 50% compared to conventional classifiers. This framework advances Industry 4.0 applications by transforming mmWave communication signals into high-precision, hardware-agnostic displacement sensors, eliminating the need for dedicated instrumentation.

Spectrum sharing technology is used to alleviate the tension and scarcity of spectrum resources, and federated learning can significantly enhance the performance of tasks such as incumbent detection and improve the quality of spectrum sharing. However, spectrum sharing methods based on federated learning still face challenges such as large-scale data transmission and the lack of privacy protection for sensing nodes. To tackle these issues, in this paper, we propose a compressed sensing (CS) based transmission framework that integrates efficient aggregation and privacy protection. In particular, a multiple measurement vector (MMV)-CS model is used for efficient aggregation between the central server and sensing nodes. By designing different measurement vectors, local environment sensing nodes can be divided into different clusters, forming multiple superimposed transmission signals at the central server. Thus, the central server will obtain the aggregated information of local models from different clusters, completing the optimization of the global model in federated learning. In this process, the efficiency of data aggregation has been greatly improved, and the data privacy of individual environment sensing nodes is protected. The security analysis and simulation results are provided to validate the effectiveness of the proposed schemes. The detection performance of the proposed method is as good as that of the approach under the raw training samples, while the privacy-preserving and communication efficiency are significantly improved.

The rapid development of artificial intelligence (AI) has brought about revolutionary changes to industrial wireless networks. Meanwhile, these AI models have also incurred a more complex security environment. This article will investigate the new situations that may arise in the industrial radio security under the support of AI technologies. First, typical radio threats and the uniqueness of industrial wireless networks are introduced. We then review existing industrial wireless physical-layer security schemes based on various AI models from the perspective of countering these radio threats. From the attackers' perspective, three typical case studies are introduced, in which AI technologies will aid in jamming, spoofing, and eavesdropping attacks. Finally, we discussed the openness issues and potential solutions in industrial radio security. This article is of significant in understanding the current status of AI-based industrial radio security, as well as the main problems and challenges. This investigation can promote the healthy development of smart factories and future industries.

Physical-layer fingerprinting is a promising technique to identify Internet of Things (IoT) devices. In this article, we investigate a new radio-frequency (RF) fingerprinting based on the distinctive signal-to-noise-ratio (SNR) trace in the sector-level sweep (SLS) procedure of 5G IEEE 802.11ad devices. This SLS SNR trace-based fingerprinting can directly apply to off-the-shelf devices without any extra hardware requirements and be independent of the wireless channel and environment. To tackle the impact of orientation on the RF fingerprinting, we propose a novel fingerprinting framework, involving correlation analysis, surface fitting, curve pursuing, and binary classification, named the CSCB framework. Using this framework, the proposed SLS SNR trace-based fingerprinting can achieve device authentication at any orientation with one receiver under line-of-sight (LOS) or non-LOS (NLOS) scenarios. We conduct proof-of-concept experiments using off-the-shelf IEEE 802.11ad devices (Talon AD7200 and MG360 WiGig) to evaluate the performance of the proposed fingerprinting schemes. Experimental results show the effectiveness of the proposed fingerprinting schemes where the verification accuracy of the proposed scheme can reach 99% with only 200 training samples.

Grant-free random access is an emerging technology for providing massive connectivity for 5G massive machine-type communications (mMTC), where non-orthogonal pilot sequences are used to simultaneously detect active users and estimate channels. However, grant-free 5G IoT networks are vulnerable to pilot contamination attacks (PCA), where the attacker can send the same pilots as legitimate IoT users to harm the active user detection and channel estimation. To defend against this attack, in this article, we propose a physical-layer countermeasure based on the channel virtual representation (CVR). CVR can emphasize the unique characteristics of mmWave channels that are sensitive to the location of the sender. This can be utilized to counter PCA no matter if the attacker's pilots are superimposed to that of the victim or not. Based on this observation, to achieve an efficient PCA detection, a single-hidden-layer multiple measurement (SHMM) Siamese network is employed. This solution tackles the challenges of channel randomness and massive connectivity in mMTC IoT networks, and supports small sample learning. Simulation results evaluate and confirm the effectiveness of the proposed detection scheme under various scenarios. The detection accuracy can approach 99% with 128 antennas at the receiver and reach above 95% even with only 50 training samples.

Spoofing attacks pose a serious threat to wireless communications. Exploiting physical-layer features to counter spoofing attacks is a promising solution. Although various physical-layer spoofing attack detection (PL-SAD) techniques have been proposed for conventional 802.11 networks in the sub-6GHz band, the study of PL-SAD for 802.11ad networks in 5G millimeter wave (mmWave) 60GHz band is largely open. In this paper, to achieve efficient PL-SAD in 5G networks, we propose a unique physical layer feature in IEEE 802.11ad networks, i.e., the signal-to-noise-ratio (SNR) trace obtained at the receiver in the sector level sweep (SLS) process. The SNR trace is readily extractable from the off-the-shelf device, and it is dependent on both transmitter location and intrinsic hardware impairment. Therefore, it can be used to achieve an efficient detection no matter the attacker is co-located with the legitimate transmitter or not. To achieve spoofing attack detection, we provide two methods based on different machine learning models. For the first method, the detection problem is formulated as a machine learning classification problem. To tackle the small sample learning and fast model construction challenges, we propose a novel neural network framework consisting of a backpropation network, a forward propagation network, and generative adversarial networks (GANs). Another method involves a Siamese network, in which the similarity between sample pairs from one device is used to achieve PL-SAD. It can tackle the training problem that the historical data cannot support the identification of the same device in a new communication session. We conduct experiments using off-the-shelf 802.11ad devices, Talon AD7200s and MG360, to evaluate the performance of the proposed PL-SAD schemes. Experimental results confirm the effectiveness of the proposed PL-SAD schemes, and the detection accuracy can reach 99% using small sample sizes under different scenarios.

Spoofing attacks pose a serious threat to wireless communications. Exploiting physical-layer features to counter spoofing attacks is a promising solution. Although various physical-layer spoofing attack detection (PL-SAD) techniques have been proposed for conventional 802.11 networks in the sub-6GHz band, the study of PL-SAD for 802.11ad networks in 5G millimeter wave (mmWave) 60GHz band is largely open. In this paper, we propose a unique physical layer feature in IEEE 802.11ad networks, i.e., the signal-to-noise-ratio (SNR) trace obtained at the receiver in the sector level sweep (SLS) process, to achieve efficient PL-SAD. The SNR trace is readily extractable from the off-the-shelf device, and it is dependent on both transmitter location and intrinsic hardware impairment. Therefore, it can be used to achieve an efficient detection no matter the attacker is co-located with the legitimate transmitter or not. The detection problem is formulated as a machine learning classification problem. To tackle the small sample learning and fast model construction challenges, we propose a novel neural network framework consisting of a backpropation network, a forward propagation network, and generative adversarial networks (GANs). It can tackle small sample learning and allow for quick model construction. We conduct experiments using off-the-shelf 802.11ad devices, Talon AD7200s and MG360, to evaluate the performance of the proposed PL-SAD scheme. Experimental results confirm the effectiveness of the proposed PL-SAD scheme, and the detection accuracy can reach 98% using small sample sizes under different scenarios.

Nonorthogonal multiple access (NOMA) technology can significantly promote Internet-of-Things (IoT) networks on spectral efficiency and massive connectivity. However, NOMA-IoT communications are vulnerable to pilot contamination attacks, where the attacker can send the same pilot signals as legitimate IoT users. Most existing countermeasures to this physical-layer threat struggle to adapt to NOMA-IoT networks, in which superimposed signals appear and low-cost IoT devices exist. In this article, we propose a compressed-sensing-based detection scheme to defend against pilot contamination attacks in NOMA-IoT networks. In particular, we present a multiple measurement vector (MMV) compressed sensing model and a security spreading code generation (SSCG) framework to prevent pilot contamination attacks from spoofing base station (BS) in NOMA-IoT networks. Furthermore, to efficiently reconstruct the superimposed signals based on the SSCG framework, a matching pursuit (MP) multiple response sparse Bayesian learning (MSBL) algorithm (MP-MSBL) is proposed. The security analysis and algorithm complexity of the proposed algorithms are provided. The simulation results evaluate and confirm the effectiveness of the proposed detection schemes. The reconstruction and detection accuracy of pilots can be higher than 99% under different scenarios.

Information security is a vital concern in Internet of Things (IoT). Traditional security method based on public or private key encryption scheme is limited by the trade‐off between low cost and high level of security. Among different security solutions, utilising compressed sensing (CS) in combination with the physical‐layer security to achieve the security is a remarkable method. However, in the current literatures, little attention has been given to the area of static environment, which will lead the risk of information leakage in the CS security model. In this study, the authors propose a new CS security model, in which circulant matrix is exploited to improve the generation efficiency of the measurement matrix, and binary resilient functions are utilised to enhance the security. Furthermore, considering the practical application, they present a feasible framework, named CS security scheme based on frequency‐selective, where the frequency‐selective feature of the wireless channel is applied to support the static environment. To verify the effectiveness of the proposed scheme, they conducted experiments and numerical simulations to evaluate the performance, and the results are satisfactory.

Spoofing attacks is one of the most critical attacks in wireless communication security. Traditional solutions are based on cryptology which is performed in the upper layers, and face many challenges especially in resource‐limited application. To overcome this hurdle, physical‐layer security has been received a lot of attention recently. In this study, the authors propose a physical‐layer spoofing detecting scheme, where signal processing and feature recognition are utilised to improve the detection performance. In this study, they present a pretreatment process based on sparse representation (SR) to reinforce the characteristic of the signal. Furthermore, they formulate the problem of spoofing detection as one of the feature extraction and recognition, and employ a developed fuzzy C‐mean algorithm to further increase the recognition accuracy. In addition, in order to verify the proposed method, they conduct experiments and use numerical simulation and analysis to evaluate the detection performance. Results showed that the proposed approach can improve the recognition accuracy significantly (increased by one order of magnitude) and the complexity is acceptable (polynomial complexity). Their findings showed that combining SR and feature extraction and recognition, the proposed method provided a good access to achieve a higher accuracy scheme of spoofing detection.

Sparse signal recovery or compressed sensing (CS) theory has recently received attention in the image compression field. CS has proven that the successful recovery rate of the multiple measurement vectors (MMVs) model is higher than that of the single measurement vector (SMV) case. Most existing algorithms have focused on sparse signal recovery using the MMV model, without considering converting the general SMV model into the MMV model. In this study, a simple transforming model that takes advantage of the correlations among wavelet coefficients is proposed, such that the MMV model can be used for general images rather than only certain special signals. To further enhance the performance of the MMV model, the improved MMV model based on the similarity of image blocks is proposed. Simulation results have shown that the obtained solution matrix can be used in the MMV model, and that the proposed algorithm provides better reconstruction quality than many state‐of‐the‐art algorithms.

Compressed Sensing (CS) theory has recently received amount of attention in the image compression filed. The sparser the signal has, the better the performance recovery. Most wavelet-based reconstruction methods of CS are developed under the assumption that the small wavelet coefficients are close to zero. In other words, a part of image information has been lost before measurement sampling. As we know, most of images have many similar areas. In order to avoid the image information being lost as little as possible, in this paper, a new CS scheme based on the similarity of image blocks is proposed in wavelet domain. Instead of processing the image as a whole, the image is firstly divided into small image blocks. And a clustering algorithm is presented to gather the similar image blocks into a group. Experiments on images demonstrate favorable performances of the proposed method.

In many wireless communication systems, data can be divided into different importance levels. For these systems, unequal error protection (UEP) techniques are used to ensure lower bit error rate for the more important classes. Moreover, if the precise characteristics of the channel are known, UEP can be used to correctly recover the more important classes even under severe receiving conditions. In this study, a UEP scheme based on compressed sensing via a linear program is proposed. Discrete wavelet transform (DWT) is chosen as the sparsifying basis, and then DWT‐coded information is divided into two‐layered coded streams, each of which is transmitted differentially by applying an unequal number of information bits in linear codes according to the time‐varying characteristic of the corrupted channel. In this proposed transmission scheme, the more important information is to guarantee error‐free transmission. At the decoder, one can simply reconstruct the signal via the l 1 ‐minimisation algorithm. Simulation results show that the proposed scheme can achieve a higher peak signal‐to‐noise ratio (PSNR) and obviously improve the error resilience compared to the equal error protection scheme and other UEP methods. More importantly, with the increase of channel corrupted ratio, the drop rate of PSNR is much slower than other solutions. It indicates that the proposed method has better robustness for severe channel conditions.