Lining Xing

Reliable data collection is essential for disaster-oriented Internet of Things (IoT) systems, where damaged terrestrial communication infrastructure often leaves sensed data buffered at disconnected end devices. In Unmanned Aerial Vehicle (UAV)-Internet of Things device (IoTD) collaborative data collection, random UAV faults and limited energy and buffer resources further complicate mission execution, making fault-tolerant scheduling crucial for robust data recovery. To address these issues, a unified framework is developed by integrating dynamic UAV reliability modeling, Maximum Distance Separable (MDS)-coded fault-tolerant backup, and collaborative scheduling optimization. Within this framework, a data fault-tolerance mechanism, termed MFTB, and a bilevel collaborative scheduling algorithm, termed LP-DCFS, are proposed. Simulation results indicate that, in the evaluated scenarios, the proposed methods achieve better overall performance than the considered baselines. In a representative high-load, high-failure scenario, MFTB reduces data loss by 4.8% and 37.5% compared with Buffer-Limited Retransmission (BLR) and Replication, respectively, while LP-DCFS increases the amount of recovered data by 33.9%, 32.3%, and 53.1% compared with ACEPSO, ADE-DMRM, and DQN, respectively. Under the modeled independent random crash and non-return faults and the evaluated simulation settings, these results suggest that coordinating failure-risk characterization, data-protection mechanisms, and task-scheduling strategies can improve the robustness and data-recovery capability of disaster-oriented UAV-assisted data collection.

Deep neural networks are vulnerable to adversarial attacks in infrared object detection. Previous infrared physical attacks have primarily targeted 2D pedestrian detection, showing limited practical effectiveness. Therefore, this paper proposes a design named Adversarial Electrothermal Clothes (AdvETC) based on a 3D human model, to attack infrared detectors from multiple viewpoints. This paper introduces a deep reinforcement learning-based optimization framework for AdvETC, enabling pedestrians to evade detection from various angles and distances. First, a 3D human model is created based on the infrared characteristics of humans in the physical world. Next, an artificial potential field is established within the search area, and a reward mechanism is introduced based on the detector's feedback and changes in the field's potential energy. Finally, trajectory points are smoothly connected using tangent-continuous Bézier curves to generate physically feasible and efficient adversarial trajectories. This paper is the first to apply graphene material in infrared adversarial attacks. By incorporating graphene-based heating fabric into the clothing based on the designed adversarial samples, the heating fabric heats up when powered, altering the infrared characteristics of the person’s surface. Due to the physical carrier's stealth, as well as the stability and continuous controllability of infrared radiation, our method significantly enhances attack effectiveness and reduces the complexity of practical implementation. Extensive experimental results show that, compared to other infrared physical attack methods, the AdvETC exhibit superior adversarial performance and robustness.

Multi-satellite hyperspectral image classification is increasingly expected to be performed on-orbit to reduce downlink and annotation costs. However, existing unsupervised domain adaptation methods typically rely on the closed-set assumption that source and target domains share the same label space, which is often violated in real multi-satellite deployments due to temporal land-cover changes and sensor upgrades. When the target domain contains previously unseen classes, directly aligning the two domains may induce negative transfer, making it difficult to learn a reliable decision boundary between known and unknown categories, especially under privacy constraints that prohibit raw data sharing. To address these challenges, we propose FedAdapt, an open-set unsupervised federated domain adaptation framework for cross-satellite hyperspectral image classification. FedAdapt first constructs class prototype vectors to induce a discriminative metric space for known classes and estimates an instance-level reliability weight for each target sample by its similarity to the prototypes. Based on this reliability, a relevance-driven weighting strategy is introduced to perform cautious adversarial domain alignment, emphasizing likely-known target samples while suppressing potential unknowns to mitigate negative transfer. In addition, an energy-based dynamic thresholding scheme is learned to adaptively separate known and unknown target samples without manual threshold tuning. Experimental results on multiple cross-scene HSI classification tasks demonstrate the effectiveness of our method.

The Earth Observation Satellite Task Scheduling Problem (EOSTSP) is an NP-Hard challenge critical for space-based information acquisition. Conventional optimization methods are hampered by high development costs, limited adaptability to dynamic scenarios, and poor interpretability. We propose a training-free solution that leverages the reasoning capabilities of Large Language Models (LLMs) through a multi-agent framework. Our approach introduces an order-driven scheduling strategy that fundamentally reconceptualizes the EOSTSP as a real-time order fulfillment process, drawing inspiration from dynamic resource allocation paradigms in complex service systems. This original methodology transforms the traditionally monolithic scheduling problem into a structured sequential decision flow, where each observation task is processed as an independent order through specialized decision phases. Implemented via the Tri- Stage LLM-Coordinated (TSLC) framework, this novel approach enables autonomous scheduling through coordinated multi-agent reasoning while maintaining full operational feasibility via external validation. Empirical results demonstrate performance improvements of 4.58% and 13.38% over state-of-the-art algorithms in routine and emergency scenarios respectively, while providing transparent interpretability through its structured decision-making process, effectively overcoming the black-box limitations of traditional optimization approaches.

This article introduces a modified fan-shaped folded waveguide resonator (FWGR) that exhibits a lower fundamental frequency, improved unloaded quality factors ( $Q_{\mathrm {u}}$ ), and a unique field distribution. Notably, the field distribution enables mixed coupling without requiring any additional structures, which is essential for realizing in-line frequency-variant coupling (FVC) filters with transmission zeros (TZs). Based on the resonator, two coupling schemes, slot coupling and gap coupling, are proposed for constructing higher-order in-line FVC filters. Comprehensive analysis, including the extraction procedure for determining the FVC coefficient and the corresponding TZs, is also presented. Three third-order in-line filters with the same in-band responses are first designed using slot coupling to demonstrate superior control of TZs, where each filter generates two independently controlled TZs due to asymmetrical structures. A fourth-order filter with three TZs is implemented based on symmetrical slots coupling further. To explore additional design possibilities, a novel kind of coupling topology integrating slots and gap couplings is proposed. One four-pole and one six-pole in-line FVC filters with a similar volume are developed for validation. In general, all developed filters in the work can achieve compact volumes and $N$ -1 TZs with simple physical structures. For experimental validation, demonstration, fourth- and sixth-order filters were selected for fabrication using 3-D metal printing technology. All prototypes were printed well, so the test results were consistent with the simulated results.

Standard data-driven fault diagnosis methods typically rely on the assumption of identical label spaces across source and target domains. However, the emergence of novel failure modes in the target domain invalidates this premise, presenting a complex open-set fault diagnosis (OSFD) challenge where traditional closed-set techniques fail to generalize. To bridge this gap, we propose a novel Adaptive Prototype Network. This framework operates through a progressive two-stage paradigm: a warm-up phase that leverages prototype learning and domain adversarial training to establish coarse-grained alignment, followed by a refinement phase that optimizes the model via adaptive clustering and dual-risk minimization. Specifically, we introduce a dynamic sample weighting mechanism guided by a learnable unknown detector to suppress negative transfer. Extensive experiments on two distinct datasets demonstrate that proposed method effectively aligns shared classes while robustly segregating unknown faults, outperforming state-of-the-art baselines.

In recent years, adversarial attacks in hyperspectral image (HSI) classification have attracted increasing attention. However, most existing approaches rely on the loss or gradient information of a single classifier to optimize pixel-level adversarial perturbations, which undermines the reflectance consistency of hyperspectral data and limits the transferability of adversarial examples across different classifier architectures. These drawbacks compromise both the physical interpretability and the practical applicability of adversarial examples. To address these challenges, this paper proposes an endmember extraction guided transferable adversarial attack (EEGTAA) framework for generating adversarial examples that preserve reflectance consistency while achieving strong transferability. Specifically, EEGTAA first employs endmember extraction techniques to obtain the endmember composition of HSIs and introduces adversarial perturbations into the endmember matrix, thereby ensuring the physical plausibility of the generated samples. Subsequently, EEGTAA integrates the loss gradients from multiple heterogeneous classifiers to optimize perturbations on the endmember matrix, enhancing the threat to target classifiers with unknown architectures and parameters. Furthermore, a conflict-mitigation gradient optimization strategy is theoretically derived, which utilizes weighted loss gradients to corrects the perturbation update direction within the hyperspherical neighborhood of the averaged gradient, alleviating the suboptimal optimization caused by divergent gradient directions across classifiers. Experimental results on benchmark HSI datasets demonstrate that EEGTAA not only produces adversarial examples with high attack performance and reflectance consistency but also exhibits superior transferability across classifier architectures.

Evolutionary multitasking optimization (EMTO) has emerged as a powerful tool for addressing complex optimization problems, particularly those involving multiple related tasks. However, current EMTO methods prioritize promoting convergence characteristics while paying little attention to potential privacy leakage issues during knowledge transfer among tasks. This paper designs privacy-preserving centralized and decentralized EMTO models based on inter-task knowledge transfer, and proposes a perturbation query strategy for the centralized EMTO. Furthermore, passive and active attacks in EMTO are proposed for the first time, and an example of active attacks in EMTO is provided by constructing a deceptive malicious task. The active attack technique can serve as a test to determine whether the EMTO methods can effectively identify and defend against malicious knowledge transfer. Experimental results show that the proposed privacy-preserving centralized EMTO method can protect clients’ privacy information while maintaining algorithm performance, and the proposed active attack technique can significantly slow down the convergence speed of the target task.