Deep joint source-channel coding (DeepJSCC) has emerged as a promising paradigm for efficient and robust information transmission. However, its intrinsic characteristics also pose new security challenges, notably an increased vulnerability to eavesdropping attacks. Existing studies on defending against eavesdropping attacks in DeepJSCC, while demonstrating certain effectiveness, often incur considerable computational overhead or introduce performance trade-offs that may adversely affect legitimate users. In this paper, we present DeepGuard, to the best of our knowledge, the first physical-layer defense framework for DeepJSCC against eavesdropping attacks, validated through over-the-air experiments using software-defined radios (SDRs). Considering that existing eavesdropping attacks against DeepJSCC are limited to simulation under ideal channels, we take a step further by identifying and implementing four representative types of attacks under various configurations in orthogonal frequency-division multiplexing systems. These attacks are evaluated over-the-air under diverse scenarios, allowing us to comprehensively characterize the real-world threat landscape. To mitigate these threats, DeepGuard introduces a novel preamble perturbation mechanism that modifies the preamble shared only between legitimate transceivers. To realize it, we first conduct a theoretical analysis of the perturbation’s impact on the signals intercepted by the eavesdropper. Building upon this, we develop an end-to-end perturbation optimization algorithm that significantly degrades eavesdropping performance while preserving reliable communication for legitimate users. We prototype DeepGuard using SDRs and conduct extensive over-the-air experiments in practical scenarios. Extensive experiments demonstrate that DeepGuard effectively mitigates eavesdropping threats while preserving reliable communication for legitimate users. In particular, DeepGuard can reduce the eavesdropper’s reconstruction performance by as much as 29 dB in PSNR and decrease classification accuracy by up to 91% compared with the performance achieved by the legitimate user.

In this article, a framework of artificial intelligence (AI)-native cross-module optimized physical layer with cooperative control agents is proposed, which involves optimization across global AI/machine learning (ML) modules of the physical layer with innovative design of multiple enhancement mechanisms and control strategies. Specifically, it achieves simultaneous optimization across global modules of uplink AI/ML-based joint source-channel coding with modulation, and downlink AI/ML-based modulation with precoding and corresponding data detection, reducing traditional inter-module information barriers to facilitate end-to-end optimization toward global objectives. Moreover, multiple enhancement mechanisms are also proposed, including i) an AI/ML-based cross-layer modulation approach with theoretical analysis for downlink transmission that breaks the isolation of inter-layer features to expand the solution space for determining improved constellation, ii) a utility-oriented precoder construction method that shifts the role of the AI/ML-based CSI feedback decoder from recovering the original CSI to directly generating precoding matrices aiming to improve end-to-end performance, and iii) incorporating modulation into AI/ML-based CSI feedback to bypass bit-level bottlenecks that introduce quantization errors, non-differentiable gradients, and limitations in constellation solution spaces. Furthermore, AI/ML-based control agents for optimized transmission schemes are proposed that leverage AI/ML to perform model switching according to channel state, thereby enabling integrated control for global throughput optimization. Finally, simulation results demonstrate the superiority of the proposed solutions in terms of block error rate and throughput. These extensive simulations employ more practical assumptions that are aligned with the requirements of the 3rd Generation Partnership Project (3GPP), which hopefully provides valuable insights for future 3GPP standardization discussions.

Complaint Large Language Model (Complaint-LLM) is designed as a "customer service" tool to address the scenario of handling a massive volume of public complaints, effectively leveraging the "common sense" possessed by Large Language Models (LLMs) to solve issues. Unfortunately, pre-trained LLMs often exhibit significant Factual Hallucination and Causal Errors in knowledge domains with sparse experience distribution, greatly affecting the accuracy of user interactions with LLMs. We propose an architecture that utilizes external data to support pre-trained models, aiming to avoid the expensive cost of retraining LLMs. The core concept involves leveraging prompts to inject strongly correlated additional information into LLMs and adjusting the initialized alternative outputs along the inference pathway of the LLM. To achieve this, we construct a rich knowledge graph as a knowledge base for algorithm retrieval and learning. Each input text is decomposed into subgraphs corresponding to nodes on the knowledge graph, and a graph neural network classifier is trained to obtain classification results and additional knowledge. Numerous experiments demonstrate that the Complaint-LLMs shows a significant improvement in the question-answering evaluation of various subclass scenarios in the complaint domain. Moreover, the graph neural network trained with complaint text data exhibits good transferability in classification tests for open scenarios.

In the upcoming next-generation (5G-Advanced and 6G) wireless networks, sensing as a service will play a more important role than ever before. Recently, the concept of perceptive network is proposed as a paradigm shift that provides sensing and communication (S&C) services simultaneously. This type of technology is typically referred to as Integrated Sensing and Communications (ISAC). In this paper, we propose the concept of sensing quality of service (QoS) in terms of diverse applications. Specifically, the probability of detection, the Crámer-Rao bound (CRB) for parameter estimation and the posterior CRB for moving target indication are employed to measure the sensing QoS for detection, localization, and tracking, respectively. Then, we establish a unified framework for ISAC resource allocation, where the fairness and the comprehensiveness optimization criteria are considered for the aforementioned sensing services. The proposed schemes can flexibly allocate the limited power and bandwidth resources according to both S&C QoSs. Finally, we study the performance trade-off between S&C services in different resource allocation schemes by numerical simulations.

The Terahertz (0.1-10 THz) band wireless data center networks (DCNs) are promising to provide high data rates and low latency for next-generation cloud applications. However, one research gap that is still existed is the lack of measurement data and thorough characterization of the THz wave propagation in data centers. To address this problem, in this paper, two sets of measurement campaigns are conducted in a data center scenario at 130–140 GHz band, by using a vector network analyzer (VNA)-based channel sounder system with different receiver heights. The measured data is further processed to extract the multi path components (MPCs) and classify the MPCs into clusters. Furthermore, the channel characteristics, including the path loss, shadow fading, K-factor, delay and angular spreads are calculated and analyzed. Clustering results and MPCs propagation are analyzed and examined in light of the real geometry in the data center. Interestingly, comparison with measured results in meeting room scenarios at 140 GHz shows that the reflections and scattering from metal racks in the data center are more significant, resulting in lower path loss, smaller K-factor, and larger delay spreads. The measured results in this work substantiate guidelines for system design of THz wireless DCNs.

Reconfigurable Intelligent Surface (RIS) has emerged as a key enabling technology to smartly reconfigure radio propagation environment for beyond the fifth generation or the sixth generation(B5G/6G) wireless communications, by adjusting the phase shifts and amplitudes of a large number of passive reflecting elements to control the signal reflection in real time. However, different from the traditional wireless base station or relay, RIS has the new feature of typically limited signaling processing capability and cannot perform active transmitting/receiving in general. So before introducing RIS into 3GPP standardization, the deployment scenario and the performance gain coming from RIS need to be studied and evaluated firstly, then the key technologies of RIS aided wireless communication including channel modeling of RIS, channel estimation and passive beamforming design need to be identified and studied, furthermore the new and unique challenges including RIS hardware imperfections for RIS deployment need to be analyzed and solved. In this paper, we provide a comprehensive survey on the key technologies research in RIS aided wireless communication system mainly in specification and implementation perspectives, and discuss some practical design and deployment problems to motivate future research and implementation of RIS.

Spatial beamforming is an efficient way to realize dual-functional radar-communication (DFRC) for integrated sensing and communications towards 6G network. In this paper, we study the DFRC design for a general scenario, where the dual-functional base station simultaneously detects the target as a MIMO radar while communicating with multiple multi-antenna communication users (CUs). This necessitates a joint transceiver beamforming design for both MIMO radar and multi-user MIMO communication. In order to avoid iterative optimization with high complexity, two low-complexity beamforming designs based on CU-selection and zero-forcing are proposed, where the closed-form expressions of the low-complexity beamforming designs are derived. Simulation results are provided to verify the effectiveness of the proposed low-complexity designs.

The over-the-air (OTA) testing based on multi-probe anechoic chamber (MPAC) is an efficient solution to evaluate the performance of 5G multiple-input multiple-output (MIMO) capable devices, which can reconstruct the wireless channel within the lab in a controlled manner. For different test requirements, the probe layouts of the MPAC may be varied, bringing a lot of additional hardware overhead. In this paper, a novel design of the MPAC test system is proposed and constructed to meet various mainstream 5G OTA test solutions. By adopting switch matrixes and the three-dimensional (3D) quick probe selection algorithm, a 3D MPAC can be easily adjusted to different probe layouts. The solution can save at most 3/4 of the hardware port resources while ensuring the channel emulation accuracy. Channel validation and 5G terminals performance testing are carried out in the new system. The result comparison demonstrates the effectiveness of the probe simplification scheme and the system design.

Over-the-Air (OTA) testing, due to its capacity of reproducing the desired radio channels in lab environments, is considered as the promising testing solution for 5G multi-input-multi-output (MIMO) devices, especially for 5G massive MIMO base station (BS). A sectored multi-probe anechoic chamber (MPAC) OTA system for 5G massive MIMO BS testing has been proposed and discussed in many literatures. The probe selection is essential for 5G BS OTA testing, since the MPAC system cost is determined by the ports of channel emulator, i.e., the number of OTA probes. However, the classical convex-optimization-based probe selection method becomes complexity-prohibitive compared with the 2D MPAC system, due to the large amount of candidate probes. This paper proposes a novel probe selection for 5G BS OTA testing with MPAC setup based on the compressed sensing theory. The simulation results indicate that the proposed method can achieve high performance over single-cluster and multi-cluster channel models, in terms of high emulation accuracy and low computational complexity.

Due to the large demand of high data rate and massive communication in mobile service, 5G network has been commercially deployed in several countries around the world. To obtain better mobile service, it is essential to complete the terminal performance test in a controllable channel environment. The conventional conducted method has been widely used in performance testing schemes for multiple-input multiple-output (MIMO) mobile terminals. With the commercialization of 5G, the terminal antenna design is becoming more complex and the connection of antenna ports via radio frequency (RF) cables will bring many practical problems. The wireless cable method is a promising alternative, which can achieve cable connection functionality without actual RF cable connections. However, the applicability of the method for higher-order MIMO terminals is mainly limited by the measurement complexity of the spatial transmission matrix. To solve this problem, a novel general reduced-order wireless cable (RWC) method is proposed in this paper, which can reduce the measurement complexity from exponential to linear without performance loss. Finally, a $4 \times 4$ MIMO 5G terminal is tested under a commercial base station (BS) and compared with the conducted method-based testing results. The result comparison demonstrates the effectiveness of the proposed RWC method.

Testing solutions of new radio (NR) multiple-input-multiple-output (MIMIO) over-the-air (OTA) are discussed currently in the 3rd generation partnership project (3GPP), and the 16 evenly spaced probes layout has been determined for frequency range1 (FR1) MIMO OTA testing, which doubles the cost compared to the long term evolution (LTE) testing solutions. A novel probe selection algorithm based on standard FR1 channel model characteristic is proposed in this paper, which can reduce cost by at least 1/8 in measurement system. Simulation results show that good constructive accuracy can be achieved for target reference channel models. Channel models verification with selected probes is further performed including the power delay profiler (PDP), the temporal correlation function (TCF), and the spatial correlation function (SCF) parameters.

In this paper, the training time minimization problem is investigated in a quantized FEEL system, where the heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels. In particular, a stochastic quantization scheme is adopted for compression of uploaded gradients, which can reduce the burden of per-round communication but may come at the cost of increasing number of communication rounds. The intrinsic trade-off between the number of communication rounds and per-round latency is characterized. Specifically, we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap. Constrained by total bandwidth, the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem. To this end, an algorithm based on alternating optimization is proposed, which alternatively solves the subproblem of quantization optimization via successive convex approximation and the subproblem of bandwidth allocation via bisection search. With different learning tasks and models, the validation of our analysis and the near-optimal performance of the proposed algorithm are demonstrated by the experimental results.

Multiple-input–multiple-output (MIMO) is a promising enabler for massive connectivity of Internet of Things (IoT) devices by offering abundance of spatial degrees of freedom. One of the challenging issues is the excessive overhead induced by users’ channel state information (CSI) feedback, which impedes the gains of MIMO techniques. The popular solution to reduce the overhead is to adopt implicit feedback. However, existing implicit feedback methods mainly rely on either expensive hardware circuits or large antenna separation, making them unaffordable to low-cost and small-factor IoT devices. To circumvent this issue, in this article, a new channel feedback mechanism calledLazyBackis proposed, which jointly calibrates multiple users’ channels by removing the hardware diversity of different users. Furthermore, to ensure up-to-date CSI, LazyBack adopts a channel prediction algorithm to infer channel stability. When the channel varies quickly over time, LazyBack switches back to the explicit feedback mode to obtain the real-time downlink channel. A LazyBack prototype is implemented based on USRPs, and the experimental results show that it provides a$1.7 \times $and$3.1 \times $throughput improvement compared with the IEEE 802.11ac for$4 \times 4$and$8 \times 8$multiuser MIMO (MU-MIMO), respectively.

Over-the-air federated edge learning(Air-FEEL) has emerged as a communication-efficient solution to enable distributed machine learning over edge devices by using their data locally to preserve the privacy. By exploiting the waveform superposition property of wireless channels, Air-FEEL allows the “one-shot” over-the-air aggregation of gradient-updates to enhance the communication efficiency, but at the cost of a compromised learning performance due to the aggregation errors caused by channel fading and noise. This paper investigates the transmission power control to combat against such aggregation errors in Air-FEEL. Different from conventional power control designs (e.g., to minimize the individualmean squared error(MSE) of the over-the-air aggregation at each round), we consider a new power control design aiming at directly maximizing the convergence speed. Towards this end, we first analyze the convergence behavior of Air-FEEL (in terms of the optimality gap) subject to aggregation errors at different communication rounds. It is revealed that if the aggregation estimates are unbiased, then the training algorithm would converge exactly to the optimal point with mild conditions; while if they are biased, then the algorithm would converge with an error floor determined by the accumulated estimate bias over communication rounds. Next, building upon the convergence results, we optimize the power control to directly minimize the derived optimality gaps under the cases without and with unbiased aggregation constraints, subject to a set of average and maximum power constraints at individual edge devices. We transform both problems into convex forms, and obtain their structured optimal solutions, both appearing in a form of regularized channel inversion, by using the Lagrangian duality method. Finally, numerical results show that the proposed power control policies achieve significantly faster convergence for Air-FEEL, as compared with benchmark policies with fixed power transmission or conventional MSE minimization.

Spatial beamforming is an efficient way to realize dual-functional radar-communication (DFRC). In this paper, we study the DFRC design for a general scenario, where the dual-functional base station (BS) simultaneously detects the target as a multiple-input-multiple-output (MIMO) radar while communicating with multiple multi-antenna communication users (CUs). This necessitates a joint transceiver beamforming design for both MIMO radar and multi-user MIMO (MU-MIMO) communication. In order to characterize the performance tradeoff between MIMO radar and MU-MIMO communication, we first define the achievable performance region of the DFRC system. Then, both radar-centric and communication-centric optimizations are formulated to achieve the boundary of the performance region. For the radar-centric optimization, successive convex approximation (SCA) method is adopted to solve the non-convex constraint. For the communication-centric optimization, a solution based on weighted mean square error (MSE) criterion is obtained to solve the non-convex objective function. Furthermore, two low-complexity beamforming designs based on CU-selection and zero-forcing are proposed to avoid iteration, and the closed-form expressions of the low-complexity beamforming designs are derived. Simulation results are provided to verify the effectiveness of all proposed designs.

Training a machine learning model with federated edge learning (FEEL) is typically time consuming due to the constrained computation power of edge devices and the limited wireless resources in edge networks. In this study, the training time minimization problem is investigated in a quantized FEEL system, where heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels. In particular, a stochastic quantization scheme is adopted for compression of uploaded gradients, which can reduce the burden of per-round communication but may come at the cost of increasing the number of communication rounds. The training time is modeled by taking into account the communication time, computation time, and the number of communication rounds. Based on the proposed training time model, the intrinsic trade-off between the number of communication rounds and per-round latency is characterized. Specifically, we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap. Furthermore, a joint data-and-model-driven fitting method is proposed to obtain the exact optimality gap, based on which the closed-form expressions for the number of communication rounds and the total training time are obtained. Constrained by the total bandwidth, the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem. To this end, an algorithm based on alternating optimization is proposed, which alternatively solves the subproblem of quantization optimization through successive convex approximation and the subproblem of bandwidth allocation by bisection search. With different learning tasks and models, the validation of our analysis and the near-optimal performance of the proposed optimization algorithm are demonstrated by the simulation results.

TeraHertz (THz) communications can satisfy the high data rate demand with massive bandwidth. However, severe path attenuation and hardware imperfection greatly alleviate its performance. Therefore, we utilize the reconfigurable intelligent surface (RIS) technology and investigate the RIS-aided THz communications. We first prove that the small-scale amplitude fading of THz signals can be accurately modeled by the fluctuating two-ray distribution based on two THz signal measurement experiments conducted in a variety of different scenarios. To optimize the phase-shifts at the RIS elements, we propose a novel swarm intelligence-based method that does not require full channel estimation. We then derive exact statistical characterizations of end-to-end signal-to-noise plus distortion ratio (SNDR) and signal-to-noise ratio (SNR). Moreover, we present asymptotic analysis to obtain more insights when the SNDR or the number of RIS’s elements is high. Finally, we derive analytical expressions for the outage probability and ergodic capacity. The tight upper bounds of ergodic capacity for both ideal and non-ideal radio frequency chains are obtained. It is interesting to find that increasing the number of RIS’s elements can significantly improve the THz communications system performance. For example, the ergodic capacity can increase up to 25% when the number of elements increases from 40 to 80, which incurs only insignificant costs to the system.

To adapt to the complicated interference and the high dynamics of wireless circumstances, deep reinforcement learning (DRL) has been considered as a potential solution for beam management in the massive multiple-input and multiple-output (MIMO) systems. However, due to the extremely high dimensions of both action and state spaces, the existing DRL-based schemes are with high computation costs, and the practical performance is still unknown. To provide some insights, DRL-based beam management in the massive MIMO systems is studied in this paper. First, a DRL-based beam management scheme has been designed for beyond the fifth generation and the sixth generation (B5G/6G) systems, which can support the collaborative beam selections of multiple panels with low complexity and fast convergence. Second, a system-level simulation platform is developed to evaluate the performance of our proposed scheme in B5G/6G systems. Finally, the system-level simulation results are provided, which show that our proposed scheme can achieve much higher spectrum efficiency than the referred evaluation results given by international telecommunication union (ITU).

Driven by the vision of intelligent connection of everything and digital twin towards 6G, a myriad of new applications, such as immersive extended reality, autonomous driving, holographic communications, intelligent industrial internet, will emerge in the near future, holding the promise to revolutionize the way we live and work. These trends inspire a novel technical design principle that seamlessly integrates two originally decoupled functionalities, i.e., wireless communication and sensing, into one system in a symbiotic way, which is dubbed symbiotic sensing and communications (SSaC), to endow the wireless network with the capability to “see” and “talk” to the physical world simultaneously. Noting that the term SSaC is used instead of ISAC (integrated sensing and communications) because the word “symbiotic/symbiosis” is more inclusive and can better accommodate different integration levels and evolution stages of sensing and communications. Aligned with this understanding, this article makes the first attempts to clarify the concept of SSaC, illustrate its vision, envision the three-stage evolution roadmap, namely neutralism, commensalism, and mutualism of SaC. Then, three categories of applications of SSaC are introduced, followed by detailed description of typical use cases in each category. Finally, we summarize the major performance metrics and key enabling technologies for SSaC.

MOTIVATION: Breast cancer is a very heterogeneous disease and there is an urgent need to design computational methods that can accurately predict the prognosis of breast cancer for appropriate therapeutic regime. Recently, deep learning-based methods have achieved great success in prognosis prediction, but many of them directly combine features from different modalities that may ignore the complex inter-modality relations. In addition, existing deep learning-based methods do not take intra-modality relations into consideration that are also beneficial to prognosis prediction. Therefore, it is of great importance to develop a deep learning-based method that can take advantage of the complementary information between intra-modality and inter-modality by integrating data from different modalities for more accurate prognosis prediction of breast cancer. RESULTS: We present a novel unified framework named genomic and pathological deep bilinear network (GPDBN) for prognosis prediction of breast cancer by effectively integrating both genomic data and pathological images. In GPDBN, an inter-modality bilinear feature encoding module is proposed to model complex inter-modality relations for fully exploiting intrinsic relationship of the features across different modalities. Meanwhile, intra-modality relations that are also beneficial to prognosis prediction, are captured by two intra-modality bilinear feature encoding modules. Moreover, to take advantage of the complementary information between inter-modality and intra-modality relations, GPDBN further combines the inter- and intra-modality bilinear features by using a multi-layer deep neural network for final prognosis prediction. Comprehensive experiment results demonstrate that the proposed GPDBN significantly improves the performance of breast cancer prognosis prediction and compares favorably with existing methods. AVAILABILITYAND IMPLEMENTATION: GPDBN is freely available at https://github.com/isfj/GPDBN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.