Peter Kipngeno Langat^*, Michael Kimwele, Dennis Kaburu

Journal of Cyber Security, Vol.8, pp. 541-558, 2026, DOI:10.32604/jcs.2026.083592 - 21 August 2026

Abstract Zero-day attacks pose a significant threat to computer systems and networks as they exploit weaknesses that have not been recognized by security professionals or software creators and for which there are no existing protective measures. This study introduced an innovative method for identifying Zero-day attacks through a Recurrent neural network model. To effectively mitigate these risks, not only is continuous monitoring essential, but also the implementation of machine learning. The model was trained on network traffic data and leveraged on the ability of Recurrent Neural Networks (RNNs) to learn complex patterns and identify anomalies that… More >

Hantian Zhang¹, Wentai Wu^2,*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.086343 - 13 August 2026

Abstract Large language models (LLMs) are increasingly used in retrieval-augmented generation (RAG) systems, where they are expected to answer questions based on retrieved evidence. In many cases, however, the right behavior is not to answer. A model should abstain when the evidence is insufficient, irrelevant, or contradictory. Existing evaluations mainly focus on final-answer accuracy, and they often pay less attention to whether models can recognize evidence quality before responding. To study this problem, we propose the Evidence Sufficiency Benchmark, a five-level benchmark for evaluating answer-abstention calibration. The benchmark covers evidence conditions from L1 Full Support to… More >

Milad Moradi^*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.086229 - 13 August 2026

Abstract Large Language Models (LLMs) have rapidly evolved into general-purpose systems with broad applicability across information access, reasoning, decision support, and human-computer interaction. Their growing deployment, however, has intensified concerns regarding safety, alignment, and robustness, especially as these models become integrated with external tools, retrieval systems, and increasingly agentic workflows. This review provides an analytical overview of the principal risks, technical advances, evaluation practices, and future directions in this area. It first clarifies the conceptual foundations of safety, alignment, robustness, and reliability in the context of LLMs. It then examines the major risk categories associated with More >

Jian Zhang¹, Seong-Min Cho², Seung-Hyun Seo^3,*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.084319 - 13 August 2026

Abstract Classical digital signature schemes such as RSA and ECDSA are threatened by the development of quantum computers, prompting the need for post-quantum cryptography (PQC). Among the various PQC candidates, multivariate quadratic (MQ) signature schemes have attracted significant attention due to their small signature size and efficient signing and verification. Evaluating these schemes is challenging because compactness, computational efficiency, and effective security are objectives that often conflict with one another and cannot usually be optimized simultaneously. In this work, we adapt a systematic multi-objective evaluation framework to MQ-based signature schemes in the NIST additional digital signature… More >

Van-Thuan Nguyen^1,2, Van-Nui Nguyen², Van-Hung Le^3,*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.081249 - 13 August 2026

Abstract The vision-language models (VLM) combine the image and text to solve practical applications. Specifically, VLM leverages the results of computer vision in conjunction with natural language processing (NLP), like a large language model (LLM), to address real-world problems such as automating and improving the quality of medical examinations and treatments in healthcare, building autonomous driving systems, image captioning, and generating automated chatbots. To understand the development and application of VLM, we surveyed VLM, classifying it according to model architecture, learning methods, evaluation measures, datasets, challenges, and future development directions of VLM based on the model… More >

Panpan Wang¹, Yanjing Liu¹, Haiyan Kong¹, Ye Li^2,*, Shuang Chen^3,*, Nong Zhou^1,*

Phyton-International Journal of Experimental Botany, Vol.95, No.7, 2026, DOI:10.32604/phyton.2026.084444 - 30 July 2026

Abstract Mulberry leaf is a widely used medicinal and edible homologous plant, and its quality is closely related to the contents of secondary metabolites. In this study, 17 batches of mulberry leaves from 3 cultivars and 7 geographical origins in Chongqing were used as materials. An HPLC method was established for the simultaneous determination of mulberroside A, chlorogenic acid, rutin, isoquercitrin, and astragalin, and the effects of cultivar and origin on the accumulation of these components were systematically compared. The established method exhibited satisfactory linearity (R² ≥ 0.9998), together with good precision, stability, repeatability, and accuracy, which… 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 >

Saeed Ullah¹, Junsheng Wu^1,*, Mian Muhammad Kamal^2,*, Mohammed K. Alzaylaee³, Heba G. Mohamed^4,5

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.084409 - 23 July 2026

Abstract The proliferation of Internet of Things (IoT) devices has introduced unprecedented security challenges, necessitating efficient intrusion detection systems (IDS) capable of operating under severe resource constraints. This research presents a hardware-informed empirical study of quantized neural-network-based intrusion detection for resource-constrained IoT platforms, using an ARM Cortex-M4 deployment target as a reference. We evaluate FP32, FP16, and INT8 TensorFlow Lite model variants derived from a lightweight 1D-CNN and assess their trade-offs in clean-data accuracy, model size, estimated inference latency, estimated energy consumption, and adversarial robustness. INT8-quantized model achieves 99.10% accuracy on clean data while maintaining 97.50%… More >

Betül Şenyayla¹, Aytuğ Onan^2,*

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.081260 - 23 July 2026

Abstract Large Language Models (LLMs) have become a cornerstone of modern natural language processing, achieving strong performance across diverse tasks. Despite these advances, their tendency to generate hallucinated or factually unsupported content remains a critical challenge for reliable deployment. Existing evaluation approaches predominantly rely on single-task settings and aggregate performance metrics, implicitly assuming that hallucination behavior is uniform across tasks. However, this assumption is fundamentally flawed, as hallucination characteristics vary significantly depending on task formulation, linguistic context, and evaluation criteria. To address these limitations, this paper proposes HalluBench, a task-aware multi-LLM benchmarking framework designed for systematic… More >

Haijun Sun^1,#, Wenyue Yan^2,#, Zhanyu Li^3,#, Qintian Li⁴, Qilong Du⁴, Li Xu⁵, Wanwei Cao³, Junrong Yang⁶, Xilan Yang², Jun Chen^7,*, Yuan Mao^8,*, Wen Huang^4,*

Oncology Research, Vol.34, No.8, 2026, DOI:10.32604/or.2026.080413 - 16 July 2026

Abstract Background: The melanoma-associated antigen-A1 (MAGE-A1) demonstrates tumor-restricted expression patterns in diverse malignancies, positioning it as an attractive therapeutic target. This investigation aimed to engineer and validate a novel antibody-drug conjugate with oxaliplatin targeting MAGE-Al (MIg-OXA), a novel antibody-drug conjugate targeting MAGE-A1, while assessing its therapeutic potential against MAGE-A1-expressing lung adenocarcinoma through both cellular and animal models. Methods: We generated a MAGE-A1-specific immunoglobulin G (IgG) antibody (MIgG) and subsequently conjugated it with oxaliplatin (OXA) to produce MIgG-OXA. The conjugate’s binding specificity and cellular uptake were verified through cell-based enzyme-linked immunosorbent assay (ELISA), flow cytometric analysis, and immunofluorescence… More >