Flying ad hoc networks (FANETs), based on unmanned aerial vehicles (UAVs), can provide innovative services in dynamic and distributed environments. However, their three-dimensional and highly mobile nature causes unstable links, rapid topology changes, and routing voids, which can degrade the performance of conventional routing protocols. This paper proposes a new proactive axis-guided 3D geographic routing approach (AxisGeo) for FANETs. It is fully distributed, maintains no routing tables, and relies only on one-hop neighbor information. AxisGeo employs two complementary geometric structures– the compressed global axis and the zoomed local axis– to adaptively guide packet forwarding. The global axis provides a fixed source-to-destination direction; whereas the local axis is proactively refined via an attraction-repulsion mechanism, where neighbor-quality information (residual energy, connectivity, progress toward destination, and expected transmission counts (ETX)) is transformed into geometric adaptation forces rather than being used directly to rank next-hop UAVs. Therefore, the proposed mechanism refines the local forwarding geometry itself before node selection. The mechanism relies only on one-hop information and requires no additional control messages beyond periodic beacon exchanges. To address routing voids, AxisGeo employs a NACK-based lightweight self-repair mechanism to reconstruct broken paths. This protocol assumes that UAVs are equipped with positioning systems and periodically exchange beacon messages to maintain one-hop neighbor information. The performance of AxisGeo was evaluated against A-Geo, UF-GPSR, and GPSR under three simulation scenarios involving variations in UAV density, UAV speed, and network traffic. Under varying node density, the packet delivery ratio (PDR) increased from 75
A bounded n-dimensional discrete hyperchaotic system is constructed to address the restricted parameter ranges and dynamical degradation commonly encountered in low-dimensional chaotic maps under finite-precision implementation. The system consists of a sinusoidal term with cyclic weighted pairwise-product coupling, a cubic cosine-feedback term cyclically arranged across dimensions, a normalization denominator, and a modulo-1 operation. Two- and three-dimensional forms are obtained as lower-dimensional realizations of the general model, while the four-dimensional form used for image encryption is selected for representative dynamical characterization through phase trajectories, Lyapunov exponent spectra, bifurcation analysis, entropy analysis, initial-condition sensitivity, and statistical tests. The representative results show that the four-dimensional form exhibits bounded state evolution, broad chaotic parameter ranges, strong trajectory divergence, and complex dynamical behavior under the tested conditions. The four-dimensional system is further used as a keystream generator for image encryption. The chaotic initial conditions, sequence offsets, and diffusion seeds are derived from an external secret key and a nonce through HMAC-SHA-512. The encryption process combines recursive multiscale permutation, state-dependent quaternary substitution, keyed global interleaving, dynamic byte substitution, and bidirectional byte diffusion. The global interleaver is placed before the single-round bidirectional byte-diffusion stage, enabling spatial redistribution and avalanche propagation to be performed at different stages. The independent 512-bit secret key provides a key space of 2^512 (approximately 10^154 ). Experimental results demonstrate exact image recovery and ciphertext-channel entropy values ranging from 7.9993 to 7.9994. When plaintext images differing in one pixel are encrypted using the same secret key and nonce, the NPCR and UACI values range from 99.5967
A novel hardware-enforced privacy protection scheme for Wireless Body Area Networks (WBANs) is proposed based on a mixed-signal lightweight homomorphic encryption architecture, addressing the challenge of patient data confidentiality in resource-constrained medical devices via analog-source integrated encryption. The core innovation is a Mixed-Signal to Ciphertext Converter (MS2CC) that replaces traditional analog-to-digital conversion with embedded encryption, enabling end-to-end data protection from acquisition to transmission. Designed in TSMC 65 nm LP CMOS technology with a 0.0286 mm2 core area, the MS2CC achieves an ultra-low 3.66 μW in post-layout simulation with RC extraction when processing clinical-grade ECG signals, achieving a three-order-of-magnitude power reduction compared with software-based homomorphic encryption implementations. A digital equivalent of the LAHE algorithm was implemented on a Xilinx Zynq-7020 FPGA for functional validation, confirming correct encryption, homomorphic addition, and decryption operations. A tailored Lightweight Additive Homomorphic Encryption (LAHE) scheme is formalized for this architecture, with rigorous theoretical derivation validating its cryptographic security and approximate additive homomorphism with bounded error. Post-layout simulation results show a 48.2 dB signal-to-noise ratio for decrypted signals and 97.9
Zero-day exploit (ZDE) attacks are among the most severe threats to critical infrastructures such as cloud computing, industrial control, smart grids, and connected vehicles, owing to their unknown, stealthy, and highly destructive nature. Traditional signature- and rule-based intrusion detection is largely ineffective against them, while existing deep learning methods struggle with global distribution modeling, local contextual dependencies, and low-sample generalization on high-dimensional, sparse, temporally correlated traffic and system-call data. This paper proposes VAE-AttNet, which fuses a Variational Autoencoder (VAE) with Multi-Head Self-Attention. Unlike prior hybrid designs that apply attention to raw features, VAE-AttNet confines self-attention to the VAE’s low-dimensional latent space and couples it with a joint anomaly score fusing reconstruction error and attention entropy. A VAE encoder maps behavioral features into a latent space via evidence-lower-bound maximization; self-attention then models context over the latent sequence, and a joint reconstruction–attention-entropy score with a dynamic 99th-percentile threshold identifies zero-day attacks. On CICIDS2017, UNSW-NB15, and ADFA-LD, VAE-AttNet reaches 97.83
Review-based recommendations commonly construct user-item interaction graphs in which textual review semantics serve as edge attributes. However, two practical limitations persist. First, raw reviews are inherently noisy: they often contain personal anecdotes, emotional expressions, and redundant phrasing that interfere with the preference-relevant signal on each edge. Second, many widely used graph contrastive learning methods generate positive views through random node or edge dropping, which may inadvertently discard semantically critical interactions and degrade the quality of learned representations. Although recent neighbor-aware methods have begun to address this limitation from structural or latent-semantic perspectives, review-based recommendation still lacks an edge-level semantic-preserving contrastive strategy that explicitly uses review evidence to protect key user-item interactions. To tackle these challenges, we propose LRGCL, an LLM-Refined Graph Contrastive Learning model for personalized recommendation. LRGCL first employs a large language model to refine each raw review into a concise, aspect-focused text that retains only key preference-feature information, and then encodes the refined review to obtain the edge semantic representation of the user-item bipartite graph. LRGCL further introduces a semantic-preserving contrastive objective in which key interaction edges are identified and preserved in augmented graph views, while only non-critical edges are dropped. Results across multiple datasets confirm that LRGCL achieves the lowest MSE and MAE among strong rating-based and review-based baselines, with especially clear MSE gains and smaller MAE margins on some domains. Ablation studies further verify the effectiveness of LLM-based review refinement and graph contrastive learning.
In the intensive care unit (ICU), the incidence of acute kidney injury (AKI) can exceed 50
Path planning is a core technology in robotics, autonomous driving systems, and unmanned aerial vehicle navigation. However, in complex environments with multiple constraints, existing intelligent optimization methods are still susceptible to factors such as uneven initial distribution, insufficient environmental feedback, and premature convergence, making it difficult to stably obtain high-quality feasible paths. To address the above problems, this paper proposes an Enhanced Competition of Tribes and Cooperation of Members Method (ECTCM) based on the competition-cooperation search framework of the Competition of Tribes and Cooperation of Members Method (CTCM), aiming to improve the global exploration capability, environmental adaptability, and local exploitation capability in complex path planning tasks. Specifically, this paper designs a double-trigonometric coupled chaotic map and combines it with opposition-based learning to construct a chaotic opposition-based initialization strategy, aiming to improve the distribution uniformity of the initial population and the coverage of the search space. An environmental quality assessment mechanism is proposed to dynamically adjust the intensity of inter-tribal competition and migration according to the environmental quality of different search regions, thereby enhancing the adaptiveness of the search direction. An improved adaptive mutation strategy is introduced to adjust the perturbation intensity based on historical memory and individual ranking information, so as to alleviate population stagnation and premature convergence. Meanwhile, an elite-guided learning evolution strategy is designed to guide inferior individuals using a weighted elite center, thereby strengthening late-stage local exploitation capability. To verify the effectiveness of the proposed method, this paper compares ECTCM with 11 mainstream optimization algorithms on the CEC2020 (D = 50, 100) and CEC2022 (D = 10, 20) benchmark test functions, and further applies it to two-dimensional (2D) grid and three-dimensional (3D) UAV path planning tasks. The experimental results show that ECTCM achieves the lowest Friedman average rank in all benchmark test scenarios, and its average win rates based on the Wilcoxon rank-sum test reach 89.1
Federated Learning (FL) facilitates collaborative training of models without exchanging any data, thereby ensuring data locality. However, the exchange of local model updates is still susceptible to attacks such as gradient inference, model reconstruction, man-in-the-middle, replay, and tampering, which create considerable privacy and security concerns. In this paper, we propose a framework for secure federated learning by combining a decentralized group key establishment scheme using ECCDH, SHA-256 based key derivation, cryptographically secure PRNG-based additive masking, and ECDSA authentication for protecting local model updates in a collaborative training process. While existing schemes require key management infrastructure, trusted third parties, or homomorphic/hyperencryption/multi-party computation techniques, our scheme allows clients to establish a common cryptographic seed in a collaborative fashion.The derived seeds are converted into synchronized masking vectors through the utilization of a secure PRNG, enabling the clients to mask their local models' updates while still maintaining compatibility with the standard FedAvg aggregation algorithm. Additionally, the use of SHA-256 and ECDSA guarantees message integrity, client authentication, and replay protection before performing the aggregation process. The formal security model and theorem prove the security properties of confidentiality, integrity, authentication, replay resistance, forward secrecy, and collusion resistance of the proposed scheme under the probabilistic polynomial-time (PPT) adversary under the hardness assumption of the ECDLP and CDH problems. The experimental study performed on five benchmark data sets (i.e., Iris, Breast Cancer, Wine, Diabetes, and Prostate Cancer) shows that the proposed framework maintains similar predictive performance as the conventional federated learning while incurring minimal overhead costs. Hence, the findings show that the proposed ECCDH-based secure aggregation framework provides an efficient and scalable way of federated learning without the use of any trusted third party.
Face Anti-Spoofing (FAS) is a crucial task for securing face recognition systems, yet its cross-domain generalization remains challenging. Recently, vision-language methods built upon pretrained models such as CLIP have shown promising performance in addressing these cross-domain scenarios. Nevertheless, existing approaches are still constrained by two primary limitations. First, fragmented spoofing cues at the patch level are typically incorporated into vision-language interactions without explicit organization, which hinders the effective exploitation of local discriminative evidence. Second, the training process generally overlooks reliability variations among samples caused by image degradation and the varying strengths of spoofing cues, allowing samples with low reliability to adversely affect the optimization process. To address these challenges, we propose Reliability-Aware Progressive Semantic Reorganization for Face Anti-Spoofing (RPSR-FAS). The framework comprises two core components: Progressive Semantic Reorganization (PSR), which reorganizes scattered local cues into more discriminative representations under the guidance of task-specific, fine-grained semantic descriptions; and Discriminative Reliability Learning (DRL), which estimates sample-level discriminative reliability via a two-stage training strategy and adaptively adjusts the contribution of different samples to the classification loss. Under a unified cross-domain evaluation protocol, RPSR-FAS is trained solely on CelebA-Spoof and directly evaluated on four unseen target domains, achieving superior average performance across these domains. Experimental results show that RPSR-FAS achieves an average Half Total Error Rate (HTER) of 4.62
Machine learning models are widely used in computer vision and classification tasks. However, imbalanced classification biases predictive models toward larger classes, reducing predictive performance for minority classes. To address this challenge, we propose meta-adaptive resampling selection plus plus (MARS + +), a stability aware meta-adaptive framework that chooses the best method based on the data. It can select from different types, such as resampling, hybrid, and algorithm-based methods. The proposed method uses inner cross-validation to test each option. It selects methods based on both performance and stability by combing predictive performance and variability across folds (mean − λ·std). It also avoids using any method if none gives clear improvement. MARS + + is tested on multiple benchmark datasets with varying imbalance levels, including both tabular and image data. We use two classifiers, the random forest and logistic regression. The results show that no single method is always the best. MARS + + still gives results close to the best choice in most cases. It also avoids the large drops in performance seen in some other methods. Statistical tests support the effectiveness of adaptive selection. This shows the importance of selecting methods based on the data. In addition, we provide a detailed analysis of method selection, and also examine cases where no method is selected. Finally, the study analyzes how close the results are to the best possible performance. It also examines how dataset features, such as imbalance and sample size, affect the method selection. These results suggest that selecting methods based on stability worked well on the evaluated datasets. They also support using an adaptive imbalance handling strategy.
Major Depressive Disorder (MDD) affects people worldwide, although electroencephalography (EEG) provides an objective neurophysiological basis for depression assessment, existing graph-based EEG frameworks suffer from several limitations. These include single-threshold brain network construction, decoupled spatiotemporal modeling, noise-sensitive population graph formation, and inadequate handling of inter-subject domain heterogeneity. To address these challenges, a Multi-Granularity Domain-Partitioned Hypergraph Spatiotemporal Network (MG-DPHSN), a novel unified end-to-end framework for EEG-based depression detection, is proposed. MG-DPHSN incorporates three complementary modules. First, a Multi-Granularity Masked Relational Learning (MG-MRL) module constructs a hierarchy of Binary Brain Networks across progressively refined threshold levels, preserving weak yet functionally relevant cortical connections. Second, an Attention-Gated 3D Graph Convolution (AG-G3D) module integrates a learnable channel-frequency attention matrix into a unified graph convolution operation, enabling simultaneous aggregation of spatial, temporal, and spectral information. Third, a Hypergraph-Embedded Secondary Subject Partitioning (H-SSP) module employs Maximum Mean Discrepancy (MMD)-based clustering to partition subjects into biologically coherent sub-domains, thereby restricting hypergraph message passing to distributionally similar subjects and mitigating inter-subject domain shift. Experiments conducted on the OpenNeuro (ds003478) demonstrate the effectiveness of the proposed framework. MG-DPHSN achieves 87.50
In recent years, constrained multi-objective optimization problems(CMOPs) remain challenging due to the complex structure of feasible regions, the difficulty of balancing convergence and diversity, and the lack of adaptive operator scheduling mechanisms. To address these issues, this paper proposes a hierarchical reinforcement learning–based subtask-coordinated scheduling method for constrained multi-objective evolutionary algorithm (HRL-SCMOE). The proposed framework employs a two-level architecture, where a high-level agent dynamically schedules subtasks–such as forward-oriented exploration, feasibility-driven exploitation, and diversity guidance–according to the environmental state, while a low-level agent adaptively selects variation operators tailored to each subtask. Both agents are trained using Double Deep Q-Networks (Double DQN) and Prioritized Experience Replay (PER) to enhance stability, sample efficiency, and value estimation reliability. Moreover, the algorithm constructs a set of collaborative information pools targeting different search objectives to maintain balanced exploration between feasible and infeasible regions. An adaptive reward mechanism and soft target updates are also incorporated to improve robustness in hierarchical policy learning. Experimental results on three benchmark test suites and four real-world application domains demonstrate that the proposed method consistently outperforms nine state-of-the-art constrained multi-objective evolutionary algorithms (CMOEAs) in terms of convergence, feasibility, and diversity, thereby confirming its effectiveness and strong general applicability.
This paper addresses the coordinated simultaneous-arrival path planning problem for multiple amphibious unmanned aerial vehicles (UAVs) operating under heterogeneous speed constraints in complex amphibious environments. Unlike conventional UAVs, amphibious UAVs must traverse both aerial and aquatic domains, which imposes distinct speed constraints and dynamic adaptability requirements. The objective is to generate collision-free, smooth trajectories that enable all UAVs to reach a common target simultaneously while respecting individual speed limits, avoiding terrain obstacles, and preventing inter-vehicle collisions. To solve this problem, we propose a novel algorithm, termed NEL_MSCPSO (neighborhood elite learning-based multi-strategy cooperative particle swarm optimization). The algorithm integrates hierarchical neighborhood reconstruction with cross-subswarm elite learning, weighted centroid-guided follower updates, fully adaptive parameter adjustment, a hybrid Gaussian-Cauchy mutation scheme with elite protection, adaptive dimensional mutation on the global best, and an enhanced differential evolution-based terminal replacement strategy. Comprehensive experiments on the CEC2022 benchmark suite demonstrate that NEL_MSCPSO achieves the lowest total rank sum among twelve state-of-the-art metaheuristic algorithms. Ablation studies confirm the necessity of each component. More importantly, the algorithm is successfully applied to four multi-amphibious UAV path planning scenarios of increasing spatial complexity, consistently producing feasible trajectories that strictly satisfy simultaneous-arrival constraints under heterogeneous speed profiles. These results demonstrate the superior engineering feasibility and robustness of NEL_MSCPSO for amphibious UAV coordination tasks.
Multimodal large language models offer strong potential for adaptive and explainable support in creative learning, but many existing systems mainly focus on content generation rather than structured guidance, progress tracking, and interpretable feedback. This paper presents TD-GAE, a Multimodal Large Language Model framework for adaptive and explainable guided art learning. The proposed method combines staged guidance using a directed acyclic graph, learner-state estimation, retrieval-augmented pedagogical context, structured feedback actions, confidence-gated critique, and safety controls to preserve learner agency and originality. Experiments were conducted on six public datasets covering sketch recognition, sketch-photo retrieval, aesthetic assessment, and fine-art style analysis, with comparisons against prompt-only, retrieval-based, planner-only, and agentic baselines. Results show that TD-GAE improves sketch interpretation by 10.2 percentage points on Quick, Draw! and 8.7 points on TU-Berlin over the prompt-only baseline. It also achieves a 22.2
Document-level relation extraction (DocRE) finds relations across a whole document. It often needs evidence from several sentences. It also needs to link repeated entity mentions and follow multi-hop clues. Many large language model (LLM) based DocRE methods use fixed relation descriptions. They make little use of confident errors or samples with missing labels. We propose SPO-PA, which combines self-correcting prompt optimization (SPO) and preference alignment (PA). SPO compares LLM predictions with reference annotations. It then revises relation descriptions, clarifies relation boundaries, and adds role constraints. PA uses false negative (FN) conflicts as the main supervision signal. It also tests false positive (FP) conflicts under similar constraints. PA applies source-specific constraints to these signals. The constraints help smaller DocRE models separate correct relations from wrong candidates. On Re-DocRED, SPO improves F1 to 26.23 PA_FN gives the most stable gains on ATLOP, KD-DocRE, DREEAM, and DAATF. The largest gain is 2.89
In post-disaster environments, the failure of terrestrial communication infrastructure necessitates the rapid deployment of unmanned aerial vehicles (UAVs) as aerial base stations to restore wireless connectivity. This paper addresses the joint UAV activation-and-placement problem in continuous space, with the objective of minimizing the number of deployed UAVs while satisfying coverage and minimum-separation constraints. To solve this problem, we propose a Hybrid K-means Quantum-Inspired Evolutionary Algorithm (HKQEA) that combines K-means-guided initialization, a calibrated penalty-based feasibility objective, non-elitist evolutionary search, and a quantum-inspired learning update. Experimental results over 50 independent runs show that HKQEA attains a best fully feasible solution with 8 UAVs, while achieving average values of 98.94
Multi-view multi-label classification has attracted increasing attention because it can characterize complex real-world data from multiple perspectives. However, the simultaneous presence of missing views and labels often causes incomplete feature information and uncertain data distributions, hindering the extraction of discriminative semantics. To address this problem, we propose a unified framework termed Reliable Cross-View Neighborhood Relation Transfer and High-Order Semantic Structure Mining (ReCHSM). Specifically, we design a reliable cross-view completion mechanism that transfers neighborhood relations from observed views to reconstruct missing ones. To reduce erroneous transfer caused by cross-view heterogeneity, the mechanism evaluates candidate-neighbor reliability and employs a lightweight nonlinear network to refine the reconstructed features. To further extract structural information from the completed representations, we introduce a random-walk-based strategy that propagates the repaired local neighborhoods to capture high-order semantic dependencies. Furthermore, considering that individual views provide different discriminative information and that the quality of completed views may vary, we develop a label-semantic-consistency-driven module to assess view quality and adaptively assign fusion weights. Extensive experiments on five public datasets demonstrate the effectiveness and competitive performance of ReCHSM.
UAV-assisted mobile edge computing (MEC) provides a flexible way to process computation-intensive tasks for ground users, but the open air-to-ground transmission links expose offloaded data to eavesdropping risks. Existing secure offloading schemes often apply fixed protection policies to all tasks, which may introduce unnecessary overhead for low-sensitivity data while providing insufficient adaptation for highly sensitive data. To address this issue, this paper proposes a rating-aware graded security offloading framework for UAV-assisted MEC networks. Each task is assigned a normalized sensitivity rating, and the rating is mapped to a security-strength coefficient that affects encryption/decryption delay, security-related energy consumption, and offloading cost. Based on this model, the offloading decision among local computing, UAV-MEC computing, and cloud computing is jointly optimized with transmission power and computing resource allocation. The resulting mixed-integer non-convex problem is solved by a tailored alternating optimization algorithm. Simulation results under the same baseline parameter settings show that the proposed framework maintains a higher offloading ratio and lower system cost than the fixed-security and no-rating baselines in the considered hover-based UAV-MEC scenario.
The rapid build-out of electric-vehicle (EV) charging infrastructure has created a protocol-rich cyber-physical attack surface that spans many independently operated charging networks. Anomaly detection across such networks is most effective when operators pool experience, yet session-level charging telemetry is commercially sensitive, privacy-regulated, and non-IID, so it cannot be centralized. Federated learning (FL) removes the need to share raw data, but plain FL leaks information through shared updates, is fragile under poisoning by malicious participants, and provides no verifiable accountability among mutually distrustful operators. We present PFAD-BC, a privacy-preserving, Byzantine-resilient, and blockchain-anchored federated anomaly-detection framework tailored to multi-operator Charge Point Operator (CPO) consortia. PFAD-BC couples an Open Charge Point Protocol (OCPP)-aware feature pipeline and an LSTM-autoencoder local detector with differentially private training under Rényi-DP accounting, a reputation-weighted cosine-similarity aggregation rule that tolerates up to f < K/3 Byzantine operators, and three permissioned-ledger contracts that record update commitments, enforce declared per-operator privacy-cap admission, register aggregation attestations, and maintain reputation state. Across two datasets—ACN-Data and the labeled-attack CICEVSE2024 benchmark—and nine baselines, PFAD-BC attains F1 = 0.736 at ϵ = 1.0 on ACN-Data (within 0.006 of the non-private centralized ceiling) and F1 = 0.896 on CICEVSE2024, leading every privacy-protected baseline. It sustains F1 ≥ 0.68 under sign-flip, Fang, and LIE attacks at a 40
Computational cost during model deployment can be reduced through knowledge distillation (KD) which transfers knowledge from a teacher model to a lightweight student model while maintaining performance. However, KD methods based on a single teacher often provide limited knowledge diversity and may transfer less informative features. Furthermore, the application of KD for plant disease classification in low-light noisy environments has received little attention. To address these limitations, we propose a KD framework using heterogeneous teachers with adaptive feature alignment (KDHT-AFA) that integrates an adaptive feature distillation switch (AFDS) to selectively align intermediate representations. For effective knowledge transfer, we propose a lightweight custom student model with 5.16 million parameters. The model incorporates a regional statistical hybrid attention (RSHA) to enhance important features semantically while increasing sensitivity to local structure and contrast. Additionally, we introduce a new self-collected real low-light plant disease dataset (ReLL-PDD v1) acquired under realistic agricultural conditions. For performance evaluation, we considered two open-source datasets, PlantVillage and the Potato Leaf Disease dataset, along with the ReLL-PDD v1 dataset. Our model achieved a mean accuracy of 86.88
