In this work, we consider a unmanned aerial vehicle (UAV)-enabled covert communication against cooperative detection. While considering the potential cooperation of wardens interfered by a jammer with pinching antennas (PAs), the first step of this work is to characterize the covert communication performance with PAs under cooperative detection. Following the characterization, a joint design of UAV trajectory, PA positions, user transmit power and user scheduling is provided, aiming at maximizing the throughput. The formulated problem is extremely hard to solve due to the complicated covert constraint involving the expression of covert communication performance, and infinite variables. To solve the problem, the characteristic of optimal transmit power and PA positions is analyzed to transform the original problem with complicated covert constraint into equivalent one only involving trajectory and user scheduling design. Next, the optimal successive-hover-and-fly structure is adopted to reformulate the problem with infinite variables into one with finite variables without loss of optimality, which can be efficiently solved via a proposed novel convex approximation method. Simulations validate the advantages of proposed scheme.

Owing to the flexible and rapid deployment capabilities, low altitude wireless network (LAWN) is gaining widespread adoption across diverse areas. Unmanned aerial vehicle (UAV), characterized by high mobility, is emerging as a pivotal component of LAWN. However, the open nature of UAV air to ground (A2G) channels render the communications highly vulnerable to illegal detection, posing a critical covert issue. This inherent vulnerability highlights the need for UAV-enabled covert communication, which aims to hide the existence of wireless transmission from illegal wardens and has attracted significant research attentions. In this article, we provide a comprehensive overview of UAV-enabled covert communication in LAWN. We first introduce typical applications and analyze emerging techniques in this domain. Subsequently, we focus on the core challenges of trajectory design, where we present two novel trajectory design methods, the successive-hover-and-fly (SHF) structure that reduces design complexity by reformulating the continuous trajectory into finite hovering points, and the artificial potential field (APF) method that, for the first time, yields a closed-form globally optimal trajectory solution. Numerical results demonstrate that these novel methods achieve near-optimal covert performance with significantly lower complexity compared to benchmark. Finally, several open directions and the challenges are discussed.

Wearable sensors with local data processing can detect health threats early, enhance documentation, and support personalized therapy. In the context of spinal cord injury (SCI), which involves risks such as pressure injuries and blood pressure instability, continuous monitoring can help mitigate these by enabling early deDtection and intervention. In this work, we present a novel distributed machine learning (DML) protocol for human activity recognition (HAR) from wearable sensor data based on gradient-boosted decision trees (XGBoost). The proposed architecture is inspired by Party-Adaptive XGBoost (PAX) while explicitly preserving key structural and optimization properties of standard XGBoost, including histogram-based split construction and tree-ensemble dynamics. First, we provide a theoretical analysis showing that, under appropriate data conditions and suitable hyperparameter selection, the proposed distributed protocol can converge to solutions equivalent to centralized XGBoost training. Second, the protocol is empirically evaluated on a representative wearable-sensor HAR dataset, reflecting the heterogeneity and data fragmentation typical of remote monitoring scenarios. Benchmarking against centralized XGBoost and IBM PAX demonstrates that the theoretical convergence properties are reflected in practice. The results indicate that the proposed approach can match centralized performance up to a gap under 1% while retaining the structural advantages of XGBoost in distributed wearable-based HAR settings.

In this work, we focus on an uncrewed aerial vehicle (UAV)-enabled covert communication with movable antenna against cooperative detection, which is still an unexplored issue. The covertness performance is first analyzed with the consideration of cooperative detection mechanism among wardens. Then, a joint design problem of segmentation ratio, transmit beamforming, trajectory and antenna position is formulated to maximize the minimal throughput among users while adhering the covertness constraint, which is extremely hard to be tackled due to the coupled variables and non-convex format. To address the problem, we develop an efficient iterative algorithm based on block coordinate descent (BCD) scheme and a novel convex approximation method, which converges to a high-quality solution efficiently. Finally, numerical results validate the benefits of our proposed scheme with respect to benchmarks.

Unmanned aerial vehicle (UAV)-enabled wireless communication technique has emerged as a promising paradigm in the next generation communication networks. However, due to the security issues arising from the inherently open nature of air to ground (A2G) links, the security of both communication behavior and information faces significant threat. To address this issue, we investigate a UAV-enabled covert and secure communication network against cooperative detection and eavesdropping from multiple illegal eves, which can share the intercepted signals with others. Specifically, from the perspective of secure communication considering channel uncertainty and cooperative eavesdropping, we characterize users' upload secure throughput by an ergodic integral expression, and formulate a max-min throughput optimization problem through joint design of UAV trajectory, user transmit power and segmentation ratio, under mobility, energy consumption and covertness constraints. Then, to address the problem with complicated covertness metric with no closed-form expression under cooperative detection, we derived closed form expressions of the covertness metric, by utilizing the Pinsker inequality along with properties of both Taylor series and the Digamma function. Subsequently, the monotonicity of the derived metric is analyzed and further utilized to simplify the covertness constraint into transmit power constraint equivalently. Afterward, a novel convex approximation method is introduced to construct a convex subproblem for the formulated highly complicated non-convex problem, enabling an efficient algorithm that delivers high-quality solutions for the formulated problem. Finally, the effectiveness and superior performance of proposed design are verified through simulations.

In this article, we consider an industrial internet of things (IIoT) network supporting multi-device dynamic ultra-reliable low-latency communication (URLLC) while the channel state information (CSI) is imperfect. A joint link adaptation (LA) and device scheduling (including the order) design is provided, aiming at maximizing the total transmission rate under strict block error rate (BLER) constraints. In particular, a Bayesian optimization (BO) driven Twin Delayed Deep Deterministic Policy Gradient (TD3) method is proposed, which determines the device served order sequence and the corresponding modulation and coding scheme (MCS) adaptively based on the imperfect CSI. Note that the imperfection of CSI, error sample imbalance in URLLC networks, as well as the parameter sensitivity nature of the TD3 algorithm likely diminish the algorithm's convergence speed and reliability. To address such an issue, we proposed a BO based training mechanism for the convergence speed improvement, which provides a more reliable learning direction and sample selection method to track the imbalance sample problem. Via extensive simulations, we show that the proposed algorithm achieves faster convergence and higher sum-rate performance compared to existing solutions.

Active learning (AL) is a machine learning (ML) approach that strategically selects the most informative samples for annotation during training, aiming to minimize annotation costs. This strategy not only reduces labeling expenses but also results in energy savings during neural network training, thereby enhancing both data and energy efficiency. In this paper, we implement and evaluate various state-of-the-art acquisition functions, analyzing their accuracy and computational costs, while discussing the advantages and disadvantages of each method. Our findings reveal that representativity-based acquisition functions effectively explore the dataset but do not prioritize boundary decisions, whereas uncertainty-based acquisition functions focus on refining boundary decisions already identified by the neural network. This trade-off is known as the exploration-exploitation dilemma. To address this dilemma, we introduce six aggregation structures: series, parallel, hybrid, adaptive feedback, random exploration, and annealing exploration. Our aggregated acquisition functions alleviate common AL pathologies such as batch mode inefficiency and the cold start problem. Additionally, we focus on balancing accuracy and energy consumption, contributing to the development of more sustainable, energy-aware artificial intelligence (AI). We evaluate our proposed structures on various models and datasets. Our results demonstrate the potential of these structures to reduce computational costs while maintaining or even improving accuracy. Innovative aggregation approaches, such as alternating between acquisition functions such as BALD and BADGE, have shown robust results. Sequentially running functions like K-Centers followed by BALD has achieved the same performance goals with up to 12% fewer samples, while reducing the acquisition cost by almost half.

The explosive growth of Industrial Internet of Things (IIoT) has been driving adoption of mobile edge computing (MEC) technique, which mitigates the tension between computation-intensive tasks and the limited capabilities of IIoT terminal devices (TDs). To meet the growing computational demands in IIoT applications, unmanned aerial vehicle (UAV)-enabled MEC has emerged as a promising framework. However, stemming from the inherent openness of air-to-ground (A2G) links, the covertness of data offloading behavior in UAV-enabled MEC is exposed to considerable risks. To address this issue, we investigate a UAV-enabled covert MEC network against the detection from an illegal warden under the assistance of multiple jammers. To enhance the computation efficiency, we formulate a joint design problem of UAV trajectory, communication resource and computation resource to maximize the computation data amount while adhering the mobility, energy consumption, resource limitation and especially the covertness constraints. Then, to address the problem with complicated covertness metric under assistance of multiple jammers, we utilize the hypothesis testing theory to derive closed-form expressions of the covertness metric, which is for the first time to analysis the covertness performance with multiple friendly jammer. Subsequently, the monotonicity of the derived metric is analyzed and further utilized to simplify the original covertness constraint into an equivalent but analyzable form. Afterward, a novel convex approximation approach is developed to construct tight convex problem, enabling an efficient algorithm to attain a high-quality solution. Finally, simulations validate the effectiveness of proposed design.

In this paper, we investigate a secure communication network assisted by two unmanned aerial vehicles (UAVs), where one UAV serves as a mobile transmitter for multiple ground users (GUs), and the other acts as a cooperative jammer to suppress a ground eavesdropper. To enhance secrecy fairness, we aim to maximize the minimum secrecy throughput among GUs by jointly optimizing UAV trajectories and communication scheduling under mobility and collision avoidance constraints. Due to the continuous-time nature of UAV mobility and the spatiotemporal coupling between the transmitter and jammer, the original problem is infinite-dimensional and non-convex. To address this, we introduce a collaborative successive hover-andfly (SHF) structure and reconstruct the UAV trajectories with a finite number of hovering and turning points. To solve the remaining non-convex problem, we introduce a minimum-distance approximation to reduce the infinite anti-collision constraints to a finite set, and adopt concave lower-bound approximations for the secrecy throughput. An efficient iterative algorithm based on successive convex approximation is developed. Simulation results demonstrate the superiority of our scheme over time-discretized and no-jamming benchmarks in terms of secrecy and complexity.

In this letter, we focus on performance analysis and UAV trajectory design for UAV-enabled covert communication under Nakagami-m channel which is still an open issue, where a joint segmentation ratio, UAV trajectory and transmit power design problem is formulated to maximize the minimal throughput under covertness constraint. To solve the complicated problem, the covert communication performance under Nakagami-m channel is first analyzed where the monotonicity of the minimal detection error probability is utilized to reformulate the original problem into a simplified one. Then, an efficient iterative algorithm based on a novel convex approximation method is proposed to solve the non-convex problem efficiently. Finally, numerical results are provided to validate the proposed scheme.

In this paper, we investigate a low-altitude wireless network (LAWN) provisioning integrated sensing and communication (ISAC) via an uncrewed aerial vehicle (UAV). The UAV is supposed to fly along a circular trajectory at a fixed height for ISAC service supply from the sky. We consider on-demand sensing services, where on-demand detection and on-demand localization requests can be activated at any time toward any position within the targeted serving region. While guaranteeing satisfactory accuracy for both on-demand sensing tasks, we aim at maximizing the minimum achievable throughput among all communication users, via joint optimizing the UAV trajectory and communication user scheduling. To address the complicated problem with infinite sensing constraints, we characterize the on-demand detection constraint as a restricted deployment area for UAV and the on-demand localization constraint as Cramér-Rao Bound (CRB) constraints over finite reference target points. Based on these characterizations, the original problem is simplified to a more tractable form. In this work, different from existing research, we target at ensuring strictly no violations of CRB constraints. To this end, we propose a convex approximation for the reformulated problem, where tight approximation is guaranteed at given local solution. The construction strategy for convex problem approximation allows an efficient iterative algorithm with verified convergence to a superior suboptimal solution. At last, with simulations, we verified the applicability of our developed approach in strictly fulfilling on-demand sensing constraints and the effectiveness of our obtained solution for simultaneously enhancing the communication throughput.

We study dual-unmanned aerial vehicle (UAV) jamming-aided secure communication networks, in which one UAV delivers confidential data to multiple ground users (GUs), while a cooperative UAV provides protective interference against a ground eavesdropper. To enforce fairness, we maximize the minimum secrecy throughput across GUs by jointly designing trajectories and communication scheduling. The key difficulty lies in the continuous-time nature of UAV trajectories and the tight space-time coupling between the transmitter and the jammer, which jointly render the problem infinite-dimensional and nonconvex. To address these challenges, we characterize, for the first time, the structure of the optimal trajectories and rigorously prove that they follow a collaborative successive hover-and-fly (co-SHF) structure, where the two UAVs visit a limited number of synchronized co-hovering point pairs, and during each flight segment at least one UAV moves at maximum speed. Leveraging this structure, we reformulate the problem into a finite-dimensional form, without loss of optimality, over hovering and turning points, hovering durations, and scheduling. For tractability, we adopt a minimum-distance approximation of continuous anti-collision constraints and employ concave lower bounds on secrecy throughput within a successive convex approximation (SCA) method, which converges and, thanks to the co-SHF reduction in optimization variables and constraints, achieves low computational complexity. Numerical results show that, compared with time-discretization and no-jamming benchmarks, the proposed co-SHF design improves the min-secrecy and user fairness while requiring significantly less runtime.

We investigate a multi-uncrewed aerial vehicle (UAV)-aided mobile edge computing (MEC) system where UAVs provide to ground devices (GDs) comprehensive services, including communication, computation, and joint decision-making (CCJD). Specifically, the system is dynamic and heterogeneous, with time-varying task requests and UAVs of diverse capabilities, data processing requirements, and priorities. To enhance the task execution efficiency, we provide a joint optimization design that minimizes the average system operation time by optimizing UAVs' three-dimensional (3D) deployment and GDs association, while adhering to no-fly zones (NFZs) and obstacle constraints. Nevertheless, the formulated problem exhibits high non-convexity with a rapidly scaling complexity w.r.t. the number of both UAVs and GDs. To address the challenges, we propose an efficient and low-complexity learning-based approach accelerated by analytical characterizations on GD's association to enhance algorithm convergence. First, we derive a closed-form solution for GD's association based on the Lagrangian dual method and optimal transmission theory (OTT). We also analytically derive the performance gap between the closed-form association and the optimal exhaustive search-based solution. Theoretical analysis demonstrates that our proposed approach achieves substantial complexity reduction compared to exhaustive search, while almost achieving the same performance. Based on the characterized optimal association, we reformulate the original joint design problem equivalently into a UAV 3D deployment optimization problem without loss of optimality, which is further established as a Markov decision process (MDP). Afterwards, an efficient algorithm based on the proposed federated multi-agent deep reinforcement learning algorithm is proposed to solve the reformulated problem, where the reward function is designed based on the closed-form GD's association and its corresponding average delay, leveraging the dueling network architecture to enhance training stability and accelerate convergence. Finally, simulation results demonstrate the superior performance of the proposed method compared to the benchmarks.

Distributed edge learning (DL) is considered a cornerstone of intelligence enablers, since it allows for collaborative training without the necessity for local clients to share raw data with other parties, thereby preserving privacy and security. Integrating DL into the 6G networks requires a coexistence design with existing services such as high-bandwidth (HB) traffic like eMBB. Current designs in the literature mainly focus on communication round-wise designs that assume a rigid resource allocation throughout each communication round (CR). However, rigid resource allocation within a CR is a highly inefficient and inaccurate representation of the system's realistic behavior. This is due to the heterogeneous nature of the system, as clients inherently may need to access the network at different times. This work zooms into one arbitrary CR, and demonstrates the importance of considering a time-dependent resource sharing design with HB traffic. We first formulate a time-step-wise optimization problem to minimize the consumed time by DL within the CR while constrained by a DL energy budget. Due to its intractability, a session-based optimization problem is formulated assuming a CR lasts less than a large-scale coherence time. Some scheduling properties of such multi-server joint communication scheduling and resource allocation framework have been established. An iterative algorithm has been designed to solve such non-convex and non-block-separable-constrained problems. Simulation results confirm the importance of the efficient and accurate integration design proposed in this work.

Distributed learning (DL) is considered a cornerstone of intelligence enabler, since it allows for collaborative training without the necessity for local clients to share raw data with other parties, thereby preserving privacy and security. Integrating DL into the 6G networks requires coexistence design with existing services such as high-bandwidth (HB) traffic like eMBB. Current designs in the literature mainly focus on communication round (CR)-wise designs that assume a fixed resource allocation during each CR. However, fixed resource allocation within a CR is a highly inefficient and inaccurate representation of the system's realistic behavior. This is due to the heterogeneous nature of the system, where clients inherently need to access the network at different times. This work zooms into one arbitrary communication round and demonstrates the importance of considering a time-dependent resource-sharing design with HB traffic. We propose a time-dependent optimization problem for minimizing the consumed time and energy by DL within the CR. Due to its intractability, a session-based optimization problem has been proposed assuming a large-scale coherence time. An iterative algorithm has been designed to solve such problems and simulation results confirm the importance of such efficient and accurate integration design.

In this paper, we investigate an integrated sensing-and-communication (ISAC) network enabled by an unmanned aerial vehicle (UAV). The UAV is supposed to fly along a periodical circular trajectory at a fixed height for ISAC service supply from the sky. We consider on-demand sensing services, where on-demand detection and on-demand localization requests may be activated at any time toward any position within the targeted serving region. While guaranteeing satisfactory accuracy for both on-demand sensing tasks, we aim at maximizing the minimum achievable throughput among all communication users, via joint optimizing the UAV trajectory and communication user scheduling. To address the complicated problem with infinite sensing constraints, we characterize the on-demand detection constraint as a restricted deployment area for UAV and the on-demand localization constraint as Cramer-Rao Bound (CRB) constraints over finite reference target points, based on which the original problem is simplified to more tractable one. Afterwards, particularly aiming to ensure no violations of CRB constraints, we propose a convex approximation for the reformulated problem, where tight approximation is guaranteed at given local solution. The construction strategy for convex problem approximation allows an efficient iterative algorithm with verified convergence to a superior suboptimal solution. At last, with simulations, we verified the applicability of our developed optimization scheme in strictly fulfilling the on-demand sensing constraints and the effectiveness of our proposed solution for simultaneously enhancing the communication throughput in UAV-enabled ISAC.

In this paper, we consider a multi-access mobile edge computing (MEC) network with multiple sensors and one MEC server in industrial Internet of Things networks, where the MEC server provides a joint computation service (in the computation phase) for a set of sub-tasks offloaded by different sensors (in the communication phase). Due to the requirements of low latency and ultra reliability, we utilize finite blocklength information theory to characterize the reliability of the communication phase and exploit extreme value theory to investigate the delay violation probability in the computation phase. Following these characterizations, we derive the average end-to-end error probability of the entire service and provide two average end-to-end reliability-optimal design frameworks considering fixed frames structure and dynamic frames structure, in both of which the goal is to minimize the average end-to-end error probability by optimally allocating the total time length to each frame, as well as allocating each frame length to the communication phase and the computation phase. For the fixed frames structure, the original problem is decomposed, and the joint convexity of the decomposed sub-problems is rigorously proved, and the optimal solutions are obtained by the proposed optimal time allocation algorithm. Moreover, for the dynamic frames structure, we reformulate the optimization problem by introducing an average time constraint. By exploiting Lagrange multipliers, we transform the reformulated optimization problem into a dual problem with strong duality, the solutions of which can be obtained by the proposed time allocation algorithm. Via simulations, we validate the proven convexity and the approximation in our analytical model and evaluate the performance for both fixed frames length structure and dynamic frames length structure.

In this paper, we study an industrial Internet of Thing (IIoT) network supporting massive ultra-reliable and low-latency communications, where each user has strict timeliness requirements. We propose an optimal framework to maximize the effective throughput via jointly choosing the uplink transmission blocklength for multiple users. To address the formulated non-convex problem, we first characterize the quasi-concavity of the effective throughput to users’ blocklength. Then, following the characterization, the problem is reformulated to a quasi-convex one. Utilizing Dinkelbach’s transformation, an efficient algorithm is developed to obtain the optimal solution. Finally, through simulations, we confirm our analytical model and the superiority of the proposed design in comparison to benchmarks.

Semantic communication has achieved great progress in improving efficiency for completing tasks successfully, instead of directly transmitting bits. However, substantial challenges remain in real-time intelligent communication, which demands stringent low latency and rapid understanding of massive data. In this paper, we propose a latency-driven design for promoting real-time multi-task multi-access semantic communications. More specifically, we investigate a deep learning-based framework for multi-access scenarios, where multiple users with individual latency requirements continuously request real-time semantic updates from an edge server. Two typical image-based semantic tasks, i.e., image classification and object detection, are considered as representative multi-task example. Furthermore, since the low-latency requirements in real-time systems force the application of finite blocklength (FBL) codes to be a significant consideration, we take into account the effects of FBL on transmission reliability. To adapt to the low-latency demands, we adopt a parameter-sharing strategy for multi-task computer vision (CV) applications and design an adaptive mixed-precision compression module for effective feature compression. The design target is to maximize the minimum weighted task success probability among all users via jointly optimizing feature extraction, mixed-precision quantization bit selection, transmit power allocation and semantic decoding. To facilitate the overall joint optimization, we propose an approach for efficient optimal decision-making on joint quantization bit selection and power allocation, which is integrated into deep learning process for adaptive feature extraction. Simulation results verify the promising performance of our proposed latency-driven design for real-time multi-task CV applications, as well as the superior benefits of our proposed efficient optimal resource allocation for real-time communication scheduling.

In this paper, we study efficient trajectory and user assignment design for an unmanned aerial vehicle (UAV)-aided covert transmission against cooperative detection from multiple wardens, which is still an open issue in the literature. Starting with analysis on basic principles of cooperative detection, we derive the closed form expression of covertness metric under cooperative detection. Then a joint design of trajectory and user assignment is formulated to maximize the minimum throughput. Although the problem is highly nonconvex with infinite variables, we adopt the optimal successive-hover-and-fly (SHF) structure to reformulated the problem and reduce the complexity without loss of optimality. Then, an efficient algorithm is developed based on a convex approximation to obtain a high-quality solution. Finally, simulations verify the necessity of considering cooperative detection and the performance advantages of proposed design.