Graph neural networks (GNNs) with differential privacy (DP) offer a reliable solution for safeguarding sensitive information within graph data. Nonetheless, existing DP-based privacy-preserving GNN learning frameworks generally overlook the local topological heterogeneity of graph nodes and tailor the same privacy budget for all nodes, which may lead to either overprotection or underprotection of some nodes, potentially diminishing model utility or posing privacy leakage risks. To address this issue, we propose a Topology-aware Differential Privacy Graph Neural Network learning framework, termed TDP-GNN, which can achieve personalized privacy protection for each node with improved privacy-utility guarantees. Specifically, TDP-GNN first identifies the topological importance of each node via an adjacency information entropy method. Then, the personalized topology-aware privacy budget is designed to quantify the privacy sensitivity of each node and adaptively allocate the privacy protection strength. Besides, a weighted neighborhood aggregation mechanism is proposed during the message-passing process of GNN training, which can eliminate the impact of the introduced differentiated DP noise on the utility of the GNN model. Since TDP-GNN is based on node-level local DP, it can be seamlessly integrated into any GNN architecture in a plug-and-play manner while ensuring formal privacy guarantees. Theoretical analysis indicates that TDP-GNN achieves ε-differential privacy over the entire graph nodes while providing personalized privacy protection. Extensive experiments demonstrate that TDP-GNN consistently yields better utilities when applied to various GNN architectures (e.g., GCN and GraphSAGE) across a diverse set of benchmarks.

In the era of 6G, with compelling visions of intelligent transportation systems and digital twins, remote surveillance is poised to become a ubiquitous practice. Substantial data volume and frequent updates present challenges in wireless networks. To address these challenges, we propose a novel agent-driven generative semantic communication (A-GSC) framework based on reinforcement learning. In contrast to the existing research on semantic communication (SemCom), which mainly focuses on either semantic extraction or semantic sampling, we seamlessly integrate both by jointly considering the intrinsic attributes of source information and the contextual information regarding the task. Notably, the introduction of generative artificial intelligence (GAI) enables the independent design of semantic encoders and decoders. In this work, we develop an agent-assisted semantic encoder with cross-modality capability, which can track the semantic changes, channel condition, to perform adaptive semantic extraction and sampling. Accordingly, we design a semantic decoder with both predictive and generative capabilities, consisting of two tailored modules. Moreover, the effectiveness of the designed models has been verified using the UA-DETRAC dataset, demonstrating the performance gains of the overall A-GSC framework in both energy saving and reconstruction accuracy.

Graph neural networks (GNNs) have been widely applied in various graph analysis tasks. To provide more convenient and faster predictive services, many enterprises are choosing to deploy GNNs in cloud environments. However, given the increasing privacy concerns about GNNs models and graph data, as well as the need to quickly generate embeddings for new nodes in real-world applications, a critical issue in this emerging paradigm is to ensure the security and scalability of GNN predictions. In this paper, we propose a privacy-preserving and scalable GNN prediction scheme, named PS-GNN, to address the privacy issues in cloud environments. Specifically, PS-GNN utilizes a customized array structure to store graph data and employs secret sharing to preserve the confidentiality of both the GNN model and graph data. Besides, the scalability of PS-GNN is achieved by aggregating feature information from local node neighborhoods in parallel. Through a detailed analysis, we demonstrate the security of PS-GNN. Extensive experiments on real-world datasets demonstrate that PS-GNN outperforms existing schemes in terms of computational and communication overhead, and reaches state-of-the-art performance on large graphs.

The burgeoning generative artificial intelligence technology offers novel insights into the development of semantic communication (SemCom) frameworks. These frameworks hold the potential to address the challenges associated with the black-box nature inherent in existing end-to-end training manner for the existing SemCom framework, as well as deterioration of the user experience caused by the inevitable error floor in deep learning-based SemCom. In this paper, we focus on the widespread remote monitoring scenario, and propose a semantic change driven generative SemCom framework. Therein, the semantic encoder and semantic decoder can be optimized independently. Specifically, we develop a modular semantic encoder with value of information based semantic sampling function. In addition, we propose a conditional denoising diffusion probabilistic mode-assisted semantic decoder that relies on received semantic information from the source, namely, the semantic map, and the local static scene information to remotely regenerate scenes. Moreover, we demonstrate the effectiveness of the proposed semantic encoder and decoder as well as the considerable potential in reducing energy consumption through simulation based on the realistic F composite channel fading model. The code is available at https://github.com/wty2011jl/SCDGSC.git.

Generative diffusion models (GDMs) have emerged as potent tools for generating high-quality, creative content across various media, including audio, images, videos, and 3-D models. Their application in artificial intelligence-generated content (AIGC) marks a pivotal advancement in the evolution from the Internet of Things (IoT) to the Artificial Intelligence of Things (AIoT). Considering the inherent multiple-access nature of AIoT, training GDMs via federated learning and deploying them collaboratively is paramount. However, such approaches introduce considerable security risks and energy consumption challenges. To address these issues, we propose a comprehensive architecture for GDMs, encompassing both training and sampling stages. This architecture, termed secure and sustainable diffusion (SS-Diff), aims to thwart trigger-based security threats, such as backdoor attacks and trojan attacks, while simultaneously reducing energy consumption in multiple-access AIoT. The SS-Diff architecture incorporates a dynamic quantization mechanism within the training phase, significantly reducing communication overhead and thereby improving both spectrum and energy efficiency. During the sampling stage, a detection-based defense strategy is employed to identify and negate trigger inputs associated with malicious attacks. Through extensive simulations, we evaluate the performance of the SS-Diff architecture. The results demonstrate that the SS-Diff can effectively train GDMs and eliminate the impact of the attacks, compared with existing schemes.

Semantic communication is an emerging paradigm for digital twin (DT) synchronization in unmanned aerial vehicle (UAV)-assisted edge computing environments, where machine learning (ML) models are deployed on edge servers and UAVs as semantic encoders and decoders to perform real-time synchronization. However, with limited system resources, additional computation workloads are still brought to all participants for semantic information extraction and recovery. In this work, we propose an optimized tiny ML-based DT synchronization framework to minimize the synchronization latency in UAV-assisted edge computing environments, considering time-average constraints on virtual energy deficit queue stability. Due to the coexistence of tiny ML-based semantic communications, a semantic extraction factor is introduced to formulate the DT synchronization problem as a time-average time minimization problem. By leveraging the Lyapunov optimization framework, the multi-stage DT synchronization problem is transformed into several per-slot resource allocation problems. To solve the per-slot optimization problem efficiently, a deep reinforcement learning-based synchronization (DRLS) algorithm is proposed, where an actor-critic structure is adopted to generate synchronization actions with low time complexity. Finally, we conduct simulation experiments to evaluate the performance of the proposed DRLS scheme. Numerical results demonstrate that our DRLS algorithm can reduce 8.23% of DT synchronization delay and 15.31% of synchronization data dropping rates on average by comparing it with the UAV-edge collaborative synchronization scheme without semantic communications. Besides, the DRLS algorithm can achieve up to 57.14% synchronization energy reduction compared with representative synchronization policies.

Owing to its practical configuration to edge computing and privacy preservation capabilities, federated learning (FL) has been increasingly appealing in Internet of Things (IoT) networks. However, due to the inherent openness of IoT network architectures, FL clients are susceptible to various attacks, resulting in unreliable local model updates. To address this challenge, federated unlearning (FU) emerges as a viable solution, which can erase such unreliable updates from the FL model using the unlearning operation while preserving model accuracy. Existing FU studies have significant potential, but they are not directly applicable to IoT networks because of their high computational costs and limited capacity to defend against prevalent dynamic attacks in mobile network environments. In this work, we propose FedRemover, a novel FU method specifically tailored for deployment in IoT networks. The key insight behind FedRemover is that model updates will exhibit inconsistency when exposed to attacks. Therefore, we devise a real-time malicious client detection scheme by examining the performance consistency of model updates. Upon detecting malicious clients, FedRemover promptly executes the unlearning operation, achieving an unlearned global model within a minimal number of rounds. This makes FedRemover highly efficient and robust against dynamic attacks, enabling it well-suited for practical deployment in IoT networks. Experiments on three standard datasets demonstrate the efficiency and robustness of FedRemover, with an obvious speed-up of 10× and comparable robustness guarantees compared with benchmark algorithms.

Recent years have witnessed a huge demand for artificial intelligence and machine learning applications in wireless edge networks to assist individuals with real-time services. Federated learning (FL) has emerged as a suitable and appealing distributed learning paradigm to deploy these applications at the network edge. Despite the many successful efforts made to apply FL to wireless edge networks, the adopted algorithms mostly follow the same spirit as FedAvg, thereby heavily suffering from the practical challenges of label deficiency and device heterogeneity. These challenges not only decelerate the model training in FL but also downgrade the application performance. In this paper, we focus on the algorithm design and address these challenges by investigating the personalized semi-supervised FL problem and proposing an effective algorithm, named FedCPSL. In particular, the techniques of pseudo-labeling, and interpolation-based model personalization are judiciously combined to provide a new problem formulation for personalized semi-supervised FL. The proposed FedCPSL algorithm employs novel strategies, including adaptive client variance reduction, local momentum, and normalized global aggregation, to combat the challenge of device heterogeneity and boost algorithm convergence. The convergence property of FedCPSL is also thoroughly analyzed and shows that FedCPSL is resilient to both statistical and system heterogeneity, obtaining a sublinear convergence rate. Experimental results on image classification tasks are presented to demonstrate that the proposed approach outperforms its counterparts in terms of both convergence speed and application performance.

Recently, federated learning (FL) has been increasingly appealing in distributed signal processing and machine learning. Nevertheless, the practical challenges of label deficiency and client heterogeneity form a bottleneck to its wide adoption. Although numerous efforts have been devoted to semi- supervised FL, most of the adopted algorithms follow the same spirit as FedAvg, thus heavily suffering from the adverse effects caused by client heterogeneity. In this paper, we boost the semi-supervised FL by addressing the issue using model personalization and client-variance-reduction. In particular, we propose a novel and unified problem formulation based on pseudo-labeling and model interpolation. We then propose an effective algorithm, named FedCPSL, which judiciously adopts the schemes of a novel momentum-based client- variance-reduction and normalized averaging. Convergence property of FedCPSL is analyzed and shows that FedCPSL is resilient to client heterogeneity and obtains a sublinear convergence rate. Experimental results on image classification tasks are also presented to demonstrate the efficacy of FedCPSL over the benchmark algorithms.

Device positioning has generally been recognized as an enabling technology for numerous vehicular applications in intelligent transportation systems (ITS). The downlink time difference of arrival (DL-TDOA) technique in cellular networks requires range information of geographically diverse base stations (BSs) to be measured by user equipment (UE) through the positioning reference signal (PRS). However, inter-cell interference from surrounding BSs can be particularly serious under poor network planning or dense deployments. This may lead to a relatively longer measurement time to locate the UE, causing an unacceptable location update rate to time-sensitive applications. In this case, PRS muting of certain wireless resources has been envisioned as a promising solution to increase the detectability of a weak BS. In this paper, to reduce UE measurement latency while ensuring high location accuracy, we propose a muting strategy managed by positioning functions that utilizes a combination of optimized pseudo-random sequences (CO-PRS) for multiple BSs to coordinate the muting of PRS resources. The original sequence is first truncated according to the muting period, and a modified greedy selection is performed to form a set of control sequences as the muting configurations (MC) with balance and concurrency constraints. Moreover, efficient information exchange can be achieved with the seeds used for regenerating the MC. Extensive simulations demonstrate that the proposed scheme outperforms the conventional random and ideal muting benchmarks in terms of measurement latency by about 30%, especially when dealing with severe near-far problems in cellular networks.

Joint network topology inference represents a canonical problem of jointly learning multiple graph Laplacian matrices from heterogeneous graph signals. In such a problem, a widely employed assumption is that of a simple common component shared among multiple graphs. However, in practice, a more intricate topological pattern, comprising simultaneously ofhomogeneousandheterogeneouscomponents, would exhibit in multiple graphs. In this paper, we propose a general graph estimator based on a novel structural fusion regularization that enables us to jointly learn multiple graphs with such complex topological patterns, and enjoys rigorous theoretical guarantees. Specifically, in the proposed regularization term, the structural similarity among graphs is characterized by a Gram matrix, which enables us to flexibly model different types of network structural similarities through different Gram matrix choices. Algorithmically, the regularization term, coupling the parameters together, makes the formulated optimization problem intractable, and thus, we develop an implementable algorithm based on the alternating direction method of multipliers (ADMM) to solve it. Theoretically, non-asymptotic statistical analysis is provided, which precisely characterizes the minimum sample size required for the consistency of the graph estimator. This analysis also provides high-probability bounds on the estimation error as a function of graph structural similarities and other key problem parameters. Finally, the superior performance of the proposed method is demonstrated through simulated and real data examples.

Abstract Recently, the physical limitation of range‐domain security guarantee for directional modulation with frequency diverse array was disclosed in Ding et al. ( IEEE Access 8, 63302–63309 (2020)). Therefore, to recreate this significant secrecy realisation in both direction and range domain, the authors conceive an artificial noise aided directional modulation scheme via reconfigurable intelligent surface. Specifically, the angle of departure from the reconfigurable intelligent surface to co‐direction receivers varies with distance, which provides the freedom to distinguish users in the range domain. With locations of the active eavesdroppers, an optimisation problem is further formulated to maximise the secrecy rate, which is then solved by applying genetic algorithm and alternating optimisation. On the other hand, when the eavesdroppers are silent, we employ maximum‐ratio transmission precoding and artificial noise to guarantee information security. Finally, simulation results demonstrate that, due to the aid of reconfigurable intelligent surface, the developed directional modulation structure can robustly guarantee the information security in the range domain, whether the information of eavesdroppers is achieved.

Abstract This paper discusses an artificial noise‐aided intelligent reflecting surface‐MIMO–OFDM system physical layer secure communication, in which two cases for the intelligent reflecting surface reflection coefficient models are considered separately, that is unit modulus constraint for the reflection coefficients and the more practical situation of amplitude phase‐shift dependence. Then the problem of joint optimisation for the precoding matrix, artificial noise covariance matrix and intelligent reflecting surface reflection coefficient matrix to maximise the sum secrecy rate under the power constraint at the transmitter is formulated, and then an alternate optimisation‐based inexact block coordinate descent algorithm is proposed to tackle the formulated non‐convexity problem. For the problem with unit modulus constraint for the intelligent reflecting surface reflection coefficients, closed‐form solutions of the optimisation variables are obtained by utilising the Lagrange multiplier method and the complex circular manifold method. For the problem with intelligent reflecting surface reflection coefficient amplitude phase‐shift dependence, alternate optimisation‐based penalty method is used to obtain the intelligent reflecting surface optimal reflection matrix. Numerical results indicate that the algorithm for the intelligent reflecting surface reflection coefficient unit modulus constraint achieves the maximum secrecy rate, and the algorithm for the intelligent reflecting surface reflection coefficient of amplitude phase‐shift dependence has the sub‐optimal performance, and the benchmark schemes such as no intelligent reflecting surface and intelligent reflecting surface random phase shift strategies have the worst and similar performance.

The revolutionary advances in machine learning and data mining techniques have contributed greatly to the rapid developments of maritime Internet of Things (IoT). In maritime IoT, the spatio-temporal vessel trajectories, collected from the hybrid satellite-terrestrial automatic identification system (AIS) base stations, are of considerable importance for promoting traffic situation awareness and vessel traffic services, etc. To guarantee traffic safety and efficiency, it is essential to robustly and accurately predict the AIS-based vessel trajectories (i.e., the future positions of vessels) in maritime IoT. In this work, we propose a spatio-temporal multigraph convolutional network (STMGCN)-based trajectory prediction framework using the mobile edge computing (MEC) paradigm. Our STMGCN is mainly composed of three different graphs, which are, respectively, reconstructed according to the social force, the time to closest point of approach, and the size of surrounding vessels. These three graphs are then jointly embedded into the prediction framework by introducing the spatio-temporal multigraph convolutional layer. To further enhance the prediction performance, the self-attention temporal convolutional layer is proposed to further optimize STMGCN with fewer parameters. Owing to the high interpretability and powerful learning ability, STMGCN is able to achieve superior prediction performance in terms of both accuracy and robustness. The reliable prediction results are potentially beneficial for traffic safety management and intelligent vehicle navigation in MEC-enabled maritime IoT.

The Multi-baseline synthetic aperture radar interferometry (InSAR) is capable of solving layover phenomena because of its resolving capability along the elevation dimension. Using baseline diversity of a multi-baseline InSAR system to overcome layover is essentially a matter of spectral estimation problem. The spectrum's period and the estimation resolution are influenced by the InSAR system parameters. This paper presents a thorough analysis of the influence of system parameters on the unambiguous height difference and the resolution of height retrieval of layover scenarios. The largest unambiguous height difference is derived and it is related to the baseline number and length. The resolution of height retrieval is determined by the signal-to-noise ratio, baseline number and multilook number. At the end, some useful advices on designing multi-baseline InSAR system parameters are presented.