Weiheng Jiang

Deep learning (DL)-driven receivers have revolutionized wireless communications but remain vulnerable to over-the-air (OTA) adversarial attacks. To address this challenge, this paper introduces an attack-agnostic, test-time adaptive frame-work for robust wireless reception. The core of this framework leverages the rich data distribution learned by a pre-trained diffusion model to purify adversarially perturbed inputs. We achieve this by projecting inputs back onto the original data manifold through a likelihood maximization (LM) process guided by denoising gradients. Concurrently, this purification process is integrated with self-ensemble inference to improve decision-making reliability. Performance evaluations demonstrate that, compared to baseline methods, the proposed framework achieves an order-of-magnitude reduction in bit error rate (BER) across a spectrum of attacks. This highlights its strong generalization, offering a promising defense solution for next-generation secure intelligent communication systems.

In smart Internet of Things (IoT) factories with dense terminal access, the communication scenarios and requirements differ significantly between ground terminals (GTs) and aerial terminals (ATs). Consequently, their demands for the two key performance indicators under URLLC constraints—Energy Efficiency (EE) and Spectral Efficiency (SE)—also exhibit distinct characteristics and variations. To achieve differentiated trade-offs between EE and SE for these two types of terminals, this letter proposes an unsupervised power allocation network (UESTPANet) and designs a differentiated trade-off mechanism. Compared with traditional iterative algorithms, it exhibits superior real-time performance and adaptability to complex scenarios. In contrast to fully supervised deep neural networks, this network can enhance the stability and real-time performance of outputs without the need for labeled training samples. Simulation results demonstrate that the proposed unsupervised method can effectively optimize the spectral efficiency and energy efficiency of the system.

This paper proposes a promising framework of multi-functional service incorporating sensing targets (STs), information receivers (IRs), and energy receivers (ERs) in an active reconfigurable intelligent surface (RIS)-aided integrated sensing, communication, and power transfer (ISCPT) system. In the proposed system, we aim to maximize the weighted sum of the received radar signal-to-interference-plus-noise-ratio (SINR) by jointly optimizing the transmit beamforming at the multi-functional base station (MFBS), the coefficients of active RIS, and the radar receive filter coefficients. Meanwhile, the constraints of the SINR of IRs, energy harvesting (EH) requirements of ERs, the power budget for the MFBS and active RIS, and the amplification gain should be satisfied. To guarantee the generality of formulated problems, we further incorporate the self-interference effects of echo signals, multi-target echo interference, simultaneous detection of multiple STs, and a nonlinear EH model into the generalized system model. Due to the presence of echo interference and multi-target echo interference, the MFBS transmits the dedicated sensing signal with the communication to enhance the sensing performance. The formulated problem is tackled by developing an efficient alternating optimization (AO) algorithm combined with fractional programming (FP) and majorization-minimization (MM) techniques. Finally, the numerical results reveal the impact of system parameters on the sensing performance, the trade-off relationship between multiple functionalities, and the deployment strategy of RIS. The main findings are as follows: 1) Active RIS is remarkably superior to passive RIS for ISCPT systems, especially for closer to the receivers with a 40 dB performance gain. 2) Comparatively, the radar sensing SINR is more sensitive to the number of active RIS units, while the SINR of IRs is more sensitive to the number of antennas at the base station. These results demonstrate that the proposed system holds the potential for practical deployment.

With the emergence of information overload in the Social Internet of Things (SIoT), personalized recommender systems (RSs) have become essential for helping users locate the items they need. Effectively modeling the heterogeneous relationships across multiple information sources and weighting them according to their varying importance, especially under sparse social interactions in the SIoT, remains a key challenge. To address this issue, this article proposes a multisource adaptive relational graph convolutional network (MARGCN) framework for RSs. User–user and user–item interactions are modeled as two relational graphs, and their embedded features are aggregated using graph convolutional networks (GCNs). A multisource relationship perception model is designed to dynamically perceive and measure the importance of multiple relationships within the graph structure, thereby enhancing the ability to recognize heterogeneous information. An adaptive information fusion model is then constructed to dynamically integrate representations from different sources through a learnable fusion strategy, avoiding information loss or redundancy caused by simple weighting. Users and items are ultimately represented by aggregating and updating their embeddings via GCNs. Experiments show that compared with the most advanced methods, MARGCN improves the hit ratio (HR) and the normalized discounted cumulative gain (NDCG) by 2.66%, 0.52%, and 3.93% in HR@5, HR@10, and HR@15, and by 1.58%, 1.32%, and 3.14% in NDCG@5, NDCG@10, and NDCG@15, respectively.