Changjun Zhou¹, Dongfang Chen¹, Chenyang Shi¹, Taiyong Li^2,*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.073662

Abstract With the rapid development of smart manufacturing, intelligent safety monitoring in industrial workshops has become increasingly important. To address the challenges of complex backgrounds, target scale variation, and excessive model parameters in worker violation detection, this study proposes ADCP-YOLO, an enhanced lightweight model based on YOLOv8. Here, “ADCP” represents four key improvements: Alterable Kernel Convolution (AKConv), Dilated-Wise Residual (DWR) module, Channel Reconstruction Global Attention Mechanism (CRGAM), and Powerful-IoU loss. These components collaboratively enhance feature extraction, multi-scale perception, and localization accuracy while effectively reducing model complexity and computational cost. Experimental results show that ADCP-YOLO achieves a More >

Haiyan Long¹, Gang Chen^2,*, Hai Chen^3,*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.073243

Abstract The performance of deep recommendation models degrades significantly under data poisoning attacks. While adversarial training methods such as Vulnerability-Aware Training (VAT) enhance robustness by injecting perturbations into embeddings, they remain limited by coarse-grained noise and a static defense strategy, leaving models susceptible to adaptive attacks. This study proposes a novel framework, Self-Purification Data Sanitization (SPD), which integrates vulnerability-aware adversarial training with dynamic label correction. Specifically, SPD first identifies high-risk users through a fragility scoring mechanism, then applies self-purification by replacing suspicious interactions with model-predicted high-confidence labels during training. This closed-loop process continuously sanitizes the training More >

Nouman Ahmad^1,*, Changsheng Zhang¹, Uroosa Sehar^2,3,4

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.073029

Abstract Although Named Entity Recognition (NER) in cybersecurity has historically concentrated on threat intelligence, vital security data can be found in a variety of sources, such as open-source intelligence and unprocessed tool outputs. When dealing with technical language, the coexistence of structured and unstructured data poses serious issues for traditional BERT-based techniques. We introduce a three-phase approach for improved NER in multi-source cybersecurity data that makes use of large language models (LLMs). To ensure thorough entity coverage, our method starts with an identification module that uses dynamic prompting techniques. To lessen hallucinations, the extraction module uses… More >

Longcang Wang, Yongbing Gao^*, Xinguang Wang, Xin Liu

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.072889

Abstract Aiming at the problem of insufficient recognition of implicit variants by existing Chinese sensitive text detection methods, this paper proposes the IPKE-MoE framework, which consists of three parts, namely, a sensitive word variant extraction framework, a sensitive word variant knowledge enhancement layer and a mixture-of-experts (MoE) classification layer. First, sensitive word variants are precisely extracted through dynamic iterative prompt templates and the context-aware capabilities of Large Language Models (LLMs). Next, the extracted variants are used to construct a knowledge enhancement layer for sensitive word variants based on RoCBert models. Specifically, after locating variants via n-gram… More >

Sooyong Jeong^1,#, Cheolhee Park^2,#, Dowon Hong^3,*, Changho Seo⁴

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.072561

Abstract With the growing complexity and decentralization of network systems, the attack surface has expanded, which has led to greater concerns over network threats. In this context, artificial intelligence (AI)-based network intrusion detection systems (NIDS) have been extensively studied, and recent efforts have shifted toward integrating distributed learning to enable intelligent and scalable detection mechanisms. However, most existing works focus on individual distributed learning frameworks, and there is a lack of systematic evaluations that compare different algorithms under consistent conditions. In this paper, we present a comprehensive evaluation of representative distributed learning frameworks—Federated Learning (FL), Split… More >

Mallikarjun P. Y.¹, Rame Gowda D. N.¹, Trisha J. K.¹, Varshini M.¹, Poornesha S. Shetty¹, Mandar Jatkar^1,*, Arpan Shah²

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.072507

Abstract As circuit feature sizes approach the nanoscale, traditional Copper (Cu) interconnects face significant hurdles posed by rising resistance-capacitance (RC) delay, electromigration, and high power dissipation. These limitations impose constraints on the scalability and reliability of future semiconductor technologies. Our paper describes the new Vertical multilayer Aluminium Boron Nitride Nanoribbon (AlBN) interconnect structure, integrated with Density functional theory (DFT) using first-principles calculations. This study explores AlBN-based nanostructures with doping of 1Cu, 2Cu, 1Fe (Iron), and 2Fe for the application of Very Large Scale Integration (VLSI) interconnects. The AlBN structure utilized the advantages of vertical multilayer interconnects… More >

Leyu Dai^1,2,3, Jindong Wang^1,2,3, Ming Zhou^1,2,3, Song Guo^1,2,3, Hengwei Zhang^1,2,3,*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.072449

Abstract In recent years, with the rapid advancement of artificial intelligence, object detection algorithms have made significant strides in accuracy and computational efficiency. Notably, research and applications of Anchor-Free models have opened new avenues for real-time target detection in optical remote sensing images (ORSIs). However, in the realm of adversarial attacks, developing adversarial techniques tailored to Anchor-Free models remains challenging. Adversarial examples generated based on Anchor-Based models often exhibit poor transferability to these new model architectures. Furthermore, the growing diversity of Anchor-Free models poses additional hurdles to achieving robust transferability of adversarial attacks. This study presents… More >

Rafiq Said Dias Jabour, Marco Antonio Luersen^*, Euclides Alexandre Bernardelli

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.072266

Abstract The roller is one of the fundamental elements of ore belt conveyor systems since it supports, guides, and directs material on the belt. This component comprises a body (the external tube) that rotates around a fixed shaft supported by easels. The external tube and shaft of rollers used in ore conveyor belts are mostly made of steel, resulting in high mass, hindering maintenance and replacement. Aiming to achieve mass reduction, we conducted a structural optimization of a roller with a polymeric external tube (hereafter referred to as a polymeric roller), seeking the optimal values for… More >

Bo Li, Jie Jia^*, Peiwen Tan, Xinyan Chen, Dongjin Li

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.071186

Abstract Medical image segmentation is of critical importance in the domain of contemporary medical imaging. However, U-Net and its variants exhibit limitations in capturing complex nonlinear patterns and global contextual information. Although the subsequent U-KAN model enhances nonlinear representation capabilities, it still faces challenges such as gradient vanishing during deep network training and spatial detail loss during feature downsampling, resulting in insufficient segmentation accuracy for edge structures and minute lesions. To address these challenges, this paper proposes the RE-UKAN model, which innovatively improves upon U-KAN. Firstly, a residual network is introduced into the encoder to effectively… More >

Dao Phuc Minh Huy¹, Gia Nhu Nguyen¹, Dac-Nhuong Le^2,*

CMC-Computers, Materials & Continua, DOI:10.32604/cmc.2025.070948

Abstract Online examinations have become a dominant assessment mode, increasing concerns over academic integrity. To address the critical challenge of detecting cheating behaviours, this study proposes a hybrid deep learning approach that combines visual detection and temporal behaviour classification. The methodology utilises object detection models—You Only Look Once (YOLOv12), Faster Region-based Convolutional Neural Network (RCNN), and Single Shot Detector (SSD) MobileNet—integrated with classification models such as Convolutional Neural Networks (CNN), Bidirectional Gated Recurrent Unit (Bi-GRU), and CNN-LSTM (Long Short-Term Memory). Two distinct datasets were used: the Online Exam Proctoring (EOP) dataset from Michigan State University and… More >