Zaid Derea^1,2,*, Beiji Zou¹, Xiaoyan Kui^1,*, Monir Abdullah³, Alaa Thobhani¹, Amr Abdussalam⁴

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 115-136, 2025, DOI:10.32604/cmc.2025.062729 - 26 March 2025

Abstract Improving website security to prevent malicious online activities is crucial, and CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) has emerged as a key strategy for distinguishing human users from automated bots. Text-based CAPTCHAs, designed to be easily decipherable by humans yet challenging for machines, are a common form of this verification. However, advancements in deep learning have facilitated the creation of models adept at recognizing these text-based CAPTCHAs with surprising efficiency. In our comprehensive investigation into CAPTCHA recognition, we have tailored the renowned UpDown image captioning model specifically for this… More >

Long Cai, Ke Gu^*, Jiaqi Lei

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 239-258, 2025, DOI:10.32604/cmc.2025.061377 - 26 March 2025

Abstract Large-scale neural networks-based federated learning (FL) has gained public recognition for its effective capabilities in distributed training. Nonetheless, the open system architecture inherent to federated learning systems raises concerns regarding their vulnerability to potential attacks. Poisoning attacks turn into a major menace to federated learning on account of their concealed property and potent destructive force. By altering the local model during routine machine learning training, attackers can easily contaminate the global model. Traditional detection and aggregation solutions mitigate certain threats, but they are still insufficient to completely eliminate the influence generated by attackers. Therefore, federated… More >

Tajinder Kumar¹, Purushottam Sharma^2,*, Xiaochun Cheng^3,*, Sachin Lalar⁴, Shubham Kumar⁵, Sandhya Bansal⁶

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 719-738, 2025, DOI:10.32604/cmc.2025.060836 - 26 March 2025

Abstract With cloud computing, large chunks of data can be handled at a small cost. However, there are some reservations regarding the security and privacy of cloud data stored. For solving these issues and enhancing cloud computing security, this research provides a Three-Layered Security Access model (TLSA) aligned to an intrusion detection mechanism, access control mechanism, and data encryption system. The TLSA underlines the need for the protection of sensitive data. This proposed approach starts with Layer 1 data encryption using the Advanced Encryption Standard (AES). For data transfer and storage, this encryption guarantees the data’s… More >

Chexiaole Zhang, Haiyan Fu^*

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1291-1306, 2025, DOI:10.32604/cmc.2025.060740 - 26 March 2025

Abstract As computer data grows exponentially, detecting anomalies within system logs has become increasingly important. Current research on log anomaly detection largely depends on log templates derived from log parsing. Word embedding is utilized to extract information from these templates. However, this method neglects a portion of the content within the logs and confronts the challenge of data imbalance among various log template types after parsing. Currently, specialized research on data imbalance across log template categories remains scarce. A dual-attention-based log anomaly detection model (LogDA), which leveraged data imbalance, was proposed to address these issues in More >

Jialiang Dong^1,2, Xuemao Dong^3,4, Zhongxue Feng^3,4,*, Caiju Li^3,4, Jianhong Yi^3,4, Jun Tan^5,*

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 65-77, 2025, DOI:10.32604/cmc.2025.059727 - 26 March 2025

Abstract To explore atomic-level phenomena in the Cu-Ni-Sn alloy, a second nearest-neighbor modified embedded-atom method (2NN MEAM) potential has been developed for the Cu-Ni-Sn system, building upon the work of other researchers. This potential demonstrates remarkable accuracy in predicting the lattice constant, with a relative error of less than 0.5% when compared to density functional theory (DFT) results, and it achieves a 10% relative error in the enthalpy of formation compared to experimental data, marking substantial advancements over prior models. The bulk modulus is predicted with a relative error of 8% compared to DFT. Notably, the More >

Zeric Tabekoueng Njitacke¹, Louai A. Maghrabi², Musheer Ahmad^3,*, Turki Althaqafi⁴

CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 917-933, 2025, DOI:10.32604/cmc.2025.059640 - 26 March 2025

Abstract This paper presents a high-security medical image encryption method that leverages a novel and robust sine-cosine map. The map demonstrates remarkable chaotic dynamics over a wide range of parameters. We employ nonlinear analytical tools to thoroughly investigate the dynamics of the chaotic map, which allows us to select optimal parameter configurations for the encryption process. Our findings indicate that the proposed sine-cosine map is capable of generating a rich variety of chaotic attractors, an essential characteristic for effective encryption. The encryption technique is based on bit-plane decomposition, wherein a plain image is divided into distinct… More >

CHRISTINA LOH¹, YUQI ZHENG¹, ISLAM ALZOUBI², KIMBERLEY L. ALEXANDER^3,4, MAGGIE LEE⁴, WEI-DONG CAI², YANG SONG⁵, KERRIE MCDONALD⁶, ANNA K. NOWAK⁷, RICHARD B. BANATI^8,9, MANUEL B. GRAEBER^1,4,10,*

Oncology Research, Vol.33, No.4, pp. 937-950, 2025, DOI:10.32604/or.2024.056436 - 19 March 2025

Abstract Background: Microglia and brain macrophages contribute significantly to the tumor microenvironment in highly malignant glioblastoma where they are considered important drivers of tumor progression. A better understanding of the role of the brain macrophages present in glioblastoma appears crucial for improving therapeutic outcomes, especially in the context of novel immunotherapeutic approaches. Methods: We investigated the regulation of two well-established markers for microglia and brain macrophages, IBA1 and CD163, in relation to glioblastoma tumor necrosis using immunohistochemistry and modality fusion heatmaps of whole slide images obtained from adjacent tissue sections. Results: IBA1 and CD163 showed remarkable differences… More >

ZHIZHENG ZHANG^1,#, TAO LI^2,#, YUAN LI³, XI WANG⁴, HAO LIU⁵, XINYU SHEN⁵, ANN XU⁶, TIANSONG XIA^1,*, BO XU^7,*

Oncology Research, Vol.33, No.4, pp. 811-819, 2025, DOI:10.32604/or.2024.050505 - 19 March 2025

Abstract Background: Breast cancer is a prevalent malignant tumor affecting females, with treatment options including surgery, radiotherapy, chemotherapy, and endocrine therapy. Methods: This review synthesizes existing literature on breast cancer stem cells and their applications in breast cancer treatment. PubMed, Web of Science, and other relevant databases were systematically searched using keywords such as “breast cancer stem cells,” “immunotherapy,” “gene therapy,” and “cell therapy.” Studies published in English were included, and their findings were analyzed to provide insights into the characteristics and therapeutic potential of breast cancer stem cells. Results: Breast cancer stem cells exhibit unique properties More >

Hamayun Khan^1,*, Muhammad Atif Imtiaz², Hira Siddique³, Muhammad Tausif Afzal Rana⁴, Arshad Ali⁵, Muhammad Zeeshan Baig⁶, Saif ur Rehman⁷, Yazed Alsaawy⁵

Computer Systems Science and Engineering, Vol.49, pp. 317-331, 2025, DOI:10.32604/csse.2025.061118 - 19 March 2025

Abstract The migration of tasks aided by machine learning (ML) predictions IN (DPM) is a system-level design technique that is used to reduce energy by enhancing the overall performance of the processor. In this paper, we address the issue of system-level higher task dissipation during the execution of parallel workloads with common deadlines by introducing a machine learning-based framework that includes task migration using energy-efficient earliest deadline first scheduling (EA-EDF). ML-based EA-EDF enhances the overall throughput and optimizes the energy to avoid delay and performance degradation in a multiprocessor system. The proposed system model allocates processors… More >

Yong An^1,2, Gang Wang^1,2, Jiangtao Dai^1,2, Zhengxia Pan^1,2, Yuhao Wu^1,2,*

Congenital Heart Disease, Vol.20, No.1, pp. 1-12, 2025, DOI:10.32604/chd.2025.063152 - 18 March 2025

Abstract Background Pulmonary arterial hypertension (PAH) is a progressive condition with a poor prognosis in children. Lung transplantation (Ltx) remains the ultimate option when patients are refractory to PAH-specific therapy. Reverse Potts shunt (RPS) has been introduced to treat suprasystemic PAH. This study aims to investigate the clinical outcomes of suprasystemic PAH in children. Methods Embase, Pubmed, and the Cochrane Library databases were searched for related studies that reported the clinical outcomes of suprasystemic PAH following RPS in children. To investigate the clinical outcomes of RPS, meta-analyses of the early and overall mortalities were performed. Results Nine studies… More >