Bingqi Gui^1,2, Shuheng Lu^1,2, Yihui Zhu^1,2,*, Zhuangqing Fan^3,4, Haiwen Sun⁵, Xuefei Yan⁶, Ang Wang⁷, Wei Pang⁷, Wenchao Chen⁷

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.1, 2026, DOI:10.32604/cmes.2026.084643 - 27 July 2026

Abstract Body armor prevents projectile penetration, but thoracic visceral injury may still result from pressure-wave transmission and back-face deformation. However, thoracic responses to single and multiple impacts remain insufficiently understood, numerical human thoracic models need further validation, and load transfer between the rib cage and cardiopulmonary system remains unclear. Therefore, this study combined live-fire blunt-impact tests on a biomimetic thoracic target with a human thoracic finite element model with filled thoracic cavity gaps. Load transfer and cardiopulmonary responses under non-penetrating rifle-bullet impact were investigated using a SiC/UHMWPE composite ballistic insert. The results showed that, first, under… More >

Li-Woei Chen¹, Kun-Lin Tsai^2,*, Fang-Yie Leu³, Chao-Tung Yang^3,4,5, Wei-Zong Liang²

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.1, 2026, DOI:10.32604/cmes.2026.083880 - 27 July 2026

Abstract Unmanned aerial vehicle (UAV) swarm networks are increasingly deployed in surveillance, disaster response, and intelligent transportation systems, where secure and efficient communication is critical under resource-constrained environments. However, conventional public-key-based security mechanisms introduce excessive computational overhead, while standalone intrusion detection systems are insufficient to defend against dynamic and multi-vector attacks in swarm networks. To address these challenges, in this paper, a lightweight time-indexed secure communication framework with intrusion detection modeling (TSCID) is proposed for resource-constrained UAV swarm networks. The proposed TSCID integrates a time-indexed session key derivation mechanism with lightweight authenticated encryption to ensure confidentiality,… More >

Weiqiang Jin^1,2,#, Yang Liu^2,#, Yang Gao^1,#, Shixiang Tang², Yanghao Zhou³, Jinhu Qi⁴, Wentao Zhang⁴, Junli Wang⁵, Jing Gao², Yue Ma⁴, Ziwei Zhang^1,*, Biao Zhao^2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.1, 2026, DOI:10.32604/cmes.2026.083586 - 27 July 2026

Abstract Large Vision-Language Models (LVLMs) have achieved strong performance in multimodal perception, understanding, and generation, but their ability to perform complex logical reasoning remains insufficiently understood. In particular, it is still unclear whether current LVLMs can reliably conduct explicit logical operations, multi-step inference, abstract relational reasoning, and cross-modal evidence integration. Reasoning abilities such as deductive, inductive, abductive, multi-hop, and causal inference are fundamental to robust decision making, trustworthy interaction, and real-world deployment, yet they have not been systematically examined in the LVLM literature. Existing surveys mainly discuss mathematical reasoning, general multimodal intelligence, or benchmark progress, but… More >

Zhuodong Liu¹, Xiangyu Li^2,*, Zhihao Zhang¹

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.085409 - 23 July 2026

Abstract Federated unlearning (FU) enables the removal of specific data contributions from federated learning (FL) models to comply with regulations such as the General Data Protection Regulation (GDPR). However, most existing FU methods are designed for the FedAvg paradigm, where all clients share a single global model. In practice, personalized federated learning (pFL) methods such as FedPer, FedRep, Ditto, and FedBN have become widely adopted due to their superior handling of non-IID data. These methods decompose the model into shared global layers and client-specific personalized layers, fundamentally altering the semantics of unlearning, yet this setting has… More >

Khanh Nguyen-Trong^1,*, Tan Nguyen-Thi-Thanh²

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.083365 - 23 July 2026

Abstract Automated wood surface defect detection is difficult to evaluate reliably because defects are often small, low-contrast, and visually confounded by natural wood texture, while reported performance can vary substantially with benchmark design and domain shift. To address this issue, we conduct a comparative study across three practically relevant settings: a curated seven-class benchmark, a broader in-domain seven-class protocol derived from the same source dataset, and supervised adaptation to a low-resource Vietnamese target domain. We compare lightweight two-stage detectors based on Faster Region-based Convolutional Neural Network (Faster R-CNN) with MobileNetV3-FPN against a compact You Only Look… More >

Hongzhen Liu¹, Liang Xie¹, Zhiqiang Ru^2,*, Yuan Wan¹, Zhe Zhang¹, Xi Fang^1,*

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082755 - 23 July 2026

Abstract Federated learning is a privacy-preserving machine learning framework that facilitates model training directly on decentralized data that, due to privacy concerns or transmission costs, cannot be centralized on a server for traditional model training. To prevent adversaries from reconstructing the original data via parameters transmitted during the process, homomorphic encryption is a commonly adopted method. However, it introduces significant communication and computation costs and risks total security failure if any secret key is compromised. This paper proposes a privacy-preserving aggregation mechanism that enables each client to independently generate partial keys for encryption while allowing decryption… More >

Akash Shah¹, Mudasir Ahmad Wani^2,*, Ravi Prakash Chaturvedi³, Shri Kant³, Nidhi Sindhwani¹, Kashish Ara Shakil⁴, Sulieman Alshuhri²

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082713 - 23 July 2026

Abstract Membership Inference Attacks (MIAs) pose a significant privacy risk in machine learning by enabling adversaries to infer whether specific data samples were used during training, particularly in sensitive domains such as social media and mental health analytics. To address this challenge, this paper proposes HEbdMIA, a lightweight homomorphic encryption-based defense that operates at the post-inference stage by encrypting model output logits without requiring retraining or architectural modifications. The proposed approach preserves the relative ordering of predictions while obscuring confidence patterns exploited by MIAs. Experimental evaluation on DepInferAttack and BotInferAttack demonstrates that HEbdMIA achieves a reduction More >

Suchang Yang, Hongtao Yu^*, Ruiyang Huang, Huansha Wang, Ran Li, Junzheng Li

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082651 - 23 July 2026

Abstract Modeling dynamic graphs in continuous time is critical for applications such as user behavior prediction and recommendation systems. These models can effectively capture fine-grained and long-term temporal dependencies. However, existing approaches often suffer from high computational costs and optimization difficulties, especially when handling time-sorted neighborhood sequences over long horizons. In this work, we propose DyG-Hyena, a novel continuous-time dynamic graph learning framework that combines conditional variational autoencoder (CVAE)-assisted temporal modeling with efficient feature fusion. Our approach has two main innovations: (i) Efficient temporal fusion—we replace the Transformer with an improved, lightweight Hyena module to model More >

Hongliang Tian, Xiaoke Liu^*, Bolin Song, Chenying Pei

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082430 - 23 July 2026

Abstract In the intelligent inspection of power systems, the detection of equipment defects is confronted with problems such as low background discrimination, multi-scale morphological differences, and the difficulty in identifying small targets and fine-grained defects, which makes it hard for existing models to balance detection accuracy and computational efficiency. To address this, this study proposes an improved lightweight detection framework, GRID-YOLO. This framework enhances the semantic discrimination ability of the backbone network for complex defects by introducing a cross-stage hierarchical multi-cognitive spatial attention module (C2MSA), designs an enhanced multi-scale bidirectional feature pyramid network (EMFPN) to achieve… More >

Kexin Zhang¹, Lihua Liu^1,*, Yuting Xue¹, Tao Zhou², Fengshuai Yue¹, Ruifeng Du¹

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082353 - 23 July 2026

Abstract Traditional Mamba-UNet integrations employ four-stage architectures, replacing conventional five-stage UNets with VMamba blocks for global dependency modeling. Unlike Transformers, which suffer from quadratic complexity and high memory consumption in self-attention, Mamba-UNet achieves efficient global modeling through linear-complexity state space modeling. This paper proposes TriLVM-UNet, a lightweight three-stage architecture that integrates parameter-efficient VMamba blocks and enhances cross-stage feature interaction via an improved skip-attention bridge (SAB) module inspired by UltraLight VM-UNet. The model incorporates a Lightweight Vision Mamba (LVM) layer for high-resolution feature extraction, alongside multi-scale dilated convolution (MSDC) and convolutional block attention module (CBAM) for enhanced More >