In the global navigation satellite system (GNSS), identifying not only single but also compound jamming signals is crucial for ensuring reliable navigation and positioning, particularly in future wireless communication scenarios such as the space-air-ground integrated network (SAGIN). However, conventional techniques often struggle with low recognition accuracy and high computational complexity, especially under low jamming-to-noise ratio (JNR) conditions. To overcome the challenge of accurately identifying compound jamming signals embedded within GNSS signals, we propose ACSNet, a novel convolutional neural network designed specifically for this purpose. Unlike conventional methods that tend to exhibit lower accuracy and higher computational demands, particularly in low JNR environments, ACSNet addresses these issues by integrating asymmetric convolution blocks, which improve sensitivity to subtle signal variations while reducing the number of parameters by approximately 50% compared to symmetric convolutional designs. Simulations demonstrate that ACSNet significantly improves accuracy in low JNR regions and shows robust resilience to power ratio (PR) variations. It achieves an overall accuracy of 91.84% and a Kappa coefficient (×100) of 90.82, and notably reaches near 100% recognition accuracy when the JNR is greater than or equal to −9 dB, confirming its effectiveness and efficiency for practical GNSS interference management applications.

Low-altitude economy (LAE) represents an emerging economic paradigm that redefines commercial and social aerial activities. Large artificial intelligence models (LAIMs) offer transformative potential to further enhance the intelligence of LAE services. However, deploying LAIMs in LAE poses several challenges, including the significant gap between their computational/storage demands and the limited onboard resources of LAE entities, the mismatch between lab-trained LAIMs and dynamic physical environments, and the inefficiencies of traditional decoupled designs for sensing, communication, and computation. To address these issues, we first propose a hierarchical system architecture tailored for LAIM deployment and present representative LAE application scenarios. Next, we explore key enabling techniques that facilitate the mutual co-evolution of LAIMs and low-altitude systems, and introduce a task-oriented execution pipeline for scalable and adaptive service delivery. Then, the proposed framework is validated through real-world case studies. Finally, we outline open challenges to inspire future research.

Secure communications in low-altitude economy networks (LAENets) are critical because the broadcast nature of air-ground links, the strong line-of-sight (LoS) propagation, and the high mobility of intelligent aerial agents (IAAs) inherently expose transmissions to agile, coordinated jamming and eavesdropping. In this paper, we consider a dynamic adversarial scenario where a legitimate IAA simultaneously provides service to multiple terrestrial receivers, while being threatened by collaborative adversarial entities comprising an intelligent UAV-based jammer and a ground-level eavesdropper. The adversaries cooperatively optimize their spatial trajectories and spectrum allocation strategies through real-time adaptive coordination. To counter such coordinated threats, we propose a synergistic framework where a lightweight retrieval-augmented generation (RAG)-enhanced large language model (LLM) predicts, from sequential wireless observations, the probabilistic jamming/eavesdropping intent distributions across frequency bands and the jammer's next-step trajectory. These predictions are then exploited by a soft actor-critic (SAC)-based reinforcement learning agent at the IAA to jointly optimize frequency-hopping selection, trajectory control, and power allocation, thereby enabling anticipatory and context-aware secure communication. Simulation results demonstrate that, compared to baseline models from deep learning (DL) and reinforcement learning (RL) approaches, our framework achieves an average secrecy-rate improvement of approximately 53.84%, while also delivering faster convergence and greater robustness against adaptive, coordinated attacks. The experiments are conducted under comparable training budgets, and our approach outperforms typical DL models (e.g., convolutional neural network (CNN), long short-term memory (LSTM), Transformer) and optimization baselines (e.g., proximal policy optimization (PPO), simulated annealing) across secrecy rate, convergence speed, and robustness. This establishes the proposed framework as a practical solution for securing next-generation LAENets under coordinated jamming and eavesdropping.

Emerging low-altitude economy networks require agile and privacy-preserving resource control under dynamic agent mobility and limited infrastructure support. To address these challenges, we propose a vision-aided integrated sensing and communication framework for intelligent aerial agent-assisted access systems, where onboard masked De-Diffusion models extract compact semantic tokens, including agent type, activity class, and heading orientation, while explicitly suppressing sensitive visual content. These tokens are fused with mmWave radar measurements to construct a semantic risk heatmap reflecting motion density, occlusion, and scene complexity, which guides access technology selection and resource scheduling. We formulate a multi-objective optimization problem to jointly maximize weighted energy and perception efficiency via radio access technology (RAT) assignment, power control, and beamforming, subject to agent-specific QoS constraints. To solve it, we develop De-Diffusion-driven vision-aided risk-aware resource optimization algorithm (DeDiff-VARARO), a novel two-stage cross-modal control algorithm: the first stage reconstructs visual scenes from tokens via De-Diffusion model for semantic parsing, while the second stage employs a deep deterministic policy gradient-based policy to adapt RAT selection, power control, and beam assignment based on fused radar-visual states. Simulation results show that DeDiff-VARARO consistently outperforms baselines in reward convergence, link robustness, and semantic fidelity, achieving within 4% of the performance of a raw-image upper bound while preserving user privacy and scalability in dense environments.

With the burgeon deployment of the fifth-generation new radio (5 G NR) networks, the codebook plays a crucial role in enabling the base station (BS) to acquire the channel state information (CSI). Different 5 G NR codebooks incur varying overheads and exhibit performance disparities under diverse channel conditions, necessitating codebook adaptation based on channel conditions to reduce feedback overhead while enhancing performance. However, existing methods of 5 G NR codebooks adaptation require significant overhead for model training and feedback or fall short in performance. To address these limitations, this letter introduces a federated reservoir computing framework designed for efficient codebook adaptation in computationally and feedback resource-constrained mobile devices. This framework utilizes a novel series of indicators as input training data, striking an effective balance between performance and feedback overhead. Compared to conventional models, the proposed codebook adaptation via federated reservoir computing (CA-FedRC), achieves rapid convergence and significant loss reduction in both speed and accuracy. Extensive simulations under various channel conditions demonstrate that our algorithm not only reduces resource consumption of users but also accurately identifies channel types, thereby optimizing the trade-off between spectrum efficiency, computational complexity, and feedback overhead.

Addressing data privacy concerns, Federated Learning (FL) has been recognized for its ability to train parameters locally on resource-constrained clients in a distributed manner. However, the problem of optimization of FL client selection and resource allocation in hierarchical Internet of Things () networks, where clients move in and out of each others' D2D communication coverage and no FL server knows all the data owners, remains open. To bridge this gap, we propose a learner referral aided federated client selection (LRef-FedCS) approach, complemented by communications and computing resource scheduling, along with local model accuracy optimization (LMAO). LRef-FedCS enhances cost efficiency and FL model quality by enabling data owners to share FL task details within their trusted local networks, increasing the opportunity of the FL server choosing the optimal clients. Using Lyapunov optimization, the problem is transformed into a joint optimization problem (JOP). To address the JOP's complexities, we combine a centralized method for LRef-FedCS and the self-adaptive global best harmony search algorithm for LMAO. For enhance scalability, a distributed LRef-FedCS based on a matching game is proposed. Numerical experiments on the Fashion-MNIST dataset show LRef-FedCS outperforms existing state-of-the-art approaches, delivering enhanced model accuracy with notable cost savings.

Integrated Sensing and Communication (ISAC) systems promise to revolutionize wireless networks by concurrently supporting high-resolution sensing and high-performance communication. This paper presents a novel radio access technology (RAT) selection framework that capitalizes on vision sensing from base station (BS) cameras to optimize both communication and perception capabilities within the ISAC system. Our framework strategically employs two distinct RATs, LTE and millimeter wave (mmWave), to enhance system performance. We propose a vision-based user localization method that employs a 3D detection technique to capture the spatial distribution of users within the surrounding environment. This is followed by geometric calculations to accurately determine the state of mmWave communication links between the BS and individual users. Additionally, we integrate the SlowFast model to recognize user activities, facilitating adaptive transmission rate allocation based on observed behaviors. We develop a Deep Deterministic Policy Gradient (DDPG)-based algorithm, utilizing the joint distribution of users and their activities, designed to maximize the total transmission rate for all users through joint RAT selection and precoding optimization, while adhering to constraints on sensing mutual information and minimum transmission rates. Numerical simulation results demonstrate the effectiveness of the proposed framework in dynamically adjusting resource allocation, ensuring high-quality communication under challenging conditions.

LEO satellites are key to global coverage in 6G wireless communications. However, efficiently selecting service satellites in multi-orbit systems remains a challenge due to dynamic topologies and limited resources. To address this challenge, this paper proposes a joint optimization framework for satellite selection, user association, and resource allocation in Space-AirGround Integrated Networks (SAGINs). We design a computationally efficient algorithm that leverages Markov approximation for satellite selection and employs matching game theory for user association and resource allocation. Our simulation results show that the proposed algorithms outperform benchmark methods.

Over-the-air computation (AirComp) enables fast data aggregation for edge intelligence applications. However the performance of AirComp can be severely degraded by channel misalignments. Pinching antenna systems (PASS) have recently emerged as a promising solution for physically reshaping favorable wireless channels to reduce misalignments and thus AirComp errors, via low-cost, fully passive, and highly reconfigurable antenna deployment. Motivated by these benefits, we propose a novel PASS-aided AirComp system that introduces new design degrees of freedom through flexible pinching antenna (PA) placement. To improve performance, we consider a mean squared error (MSE) minimization problem by jointly optimizing the PA position, transmit power, and decoding vector. To solve this highly non-convex problem, we propose an alternating optimization based framework with alternating linear search based PA position updates. Simulation results show that our proposed joint PA position and communication design significantly outperforms various benchmark schemes in AirComp accuracy.

In the era of smart cyber-physical grid, dynamic insecurity risk has become a significant concern due to the increasing integration of renewable energy sources and the inherent uncertainties in smart grid. Dynamic security assessment (DSA) has been adopted to hedge against such risks by estimating the stability of large-scale smart grids. Existing DSA approaches often involve complex high dimensional models which incur high communication and computational costs, hindering their practical adoption. In this paper, we address these limitations with the Quantum Federated Ensembled Variational Adaptive Learning (QFEVAL) approach for smart grid DSA. QFEVAL is designed to combine quantum machine learning and federated learning to handle the differential-algebraic equations that describe smart grid stability, providing an efficient way to deal with high-dimensional data and uncertainties. QFEVAL enables the training of the hybrid quantum-classical neural networks on distributed DSA datasets located at different nodes in smart grids, without requiring large numbers of parameters to be transmitted. QFEVAL accurately predicts the stability of the smart grid under various conditions, enabling the implementation of preventive stability control measures. Through extensive experiments, we demonstrate that QFEVAL achieves comparable performance to 9 state-of-the-art DSA approaches with more than 2 orders of magnitude fewer model parameter transmissions. QFEVAL paves the way for reliable, secure, and continuous electricity supply, offering a robust solution to the challenges of DSA in smart grids.