High-Confidence Computing最新文献

Pluggable AI-based real-time stragglers detection framework in Hadoop Hadoop中可插入的基于人工智能的实时掉队检测框架

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-07-03 DOI: 10.1016/j.hcc.2025.100341

Xinyuan Liu, Yinhao Li, Rajiv Ranjan, Devki Nandan Jha

The growing reliance on big data frameworks such as Hadoop has revolutionized data processing across various domains, enabling large-scale storage and distributed computation. Hadoop is widely employed in real-world applications such as high-performance computation tasks, e-commerce and data analysis in healthcare. However, the efficiency of Hadoop systems is often hampered by faults and anomalies, with stragglers emerging as one of the most prevalent issues. Stragglers disrupt workflows, waste resources and degrade system performance. While existing anomaly detection models employ methods like median analysis or static thresholds, they often struggle with issues such as high false positives, lack of adaptability and poor handling of complex heterogeneous environments. To address these challenges, this paper presents Plabs, a flexible stragglers detection framework for Hadoop. The framework comprises two core components: (1) a Monitoring Module providing real-time tracking of cluster resources and task progress and (2) a Pluggable AI-based straggler detection module, designed for precise straggler task identification. By leveraging advanced monitoring and AI-driven analysis, Plabs offers an automated, flexible and scalable solution for detecting stragglers at run-time in Hadoop clusters. We evaluated Plabs exhaustively with three Machine Learning (ML), two Deep Learning (DL) and two Large Language Models (LLMs) on five different applications in a real testbed environment. Our experiment evaluation shows that DL models outperform others in identifying Hadoop stragglers, achieving superior accuracy and reliability for all the applications.

对Hadoop等大数据框架的日益依赖已经彻底改变了跨各个领域的数据处理，使大规模存储和分布式计算成为可能。Hadoop被广泛应用于现实世界的应用程序中，如高性能计算任务、电子商务和医疗保健领域的数据分析。然而，Hadoop系统的效率经常受到故障和异常的阻碍，掉队者成为最普遍的问题之一。掉队者扰乱工作流程，浪费资源，降低系统性能。虽然现有的异常检测模型采用了中位数分析或静态阈值等方法，但它们经常会遇到误报率高、适应性不足以及对复杂异构环境处理能力差等问题。为了应对这些挑战，本文提出了Plabs，一个灵活的Hadoop掉队检测框架。该框架包括两个核心组件：(1)监控模块，提供集群资源和任务进度的实时跟踪；(2)基于Pluggable ai的掉队者检测模块，用于精确识别掉队者任务。通过利用先进的监控和人工智能驱动的分析，Plabs提供了一个自动化、灵活和可扩展的解决方案，用于在Hadoop集群的运行时检测掉队者。我们在一个真实的测试平台环境中，用三个机器学习（ML），两个深度学习（DL）和两个大型语言模型（llm）在五个不同的应用程序上对Plabs进行了详尽的评估。我们的实验评估表明，深度学习模型在识别Hadoop掉队者方面优于其他模型，为所有应用程序实现了卓越的准确性和可靠性。

{"title":"Pluggable AI-based real-time stragglers detection framework in Hadoop","authors":"Xinyuan Liu, Yinhao Li, Rajiv Ranjan, Devki Nandan Jha","doi":"10.1016/j.hcc.2025.100341","DOIUrl":"10.1016/j.hcc.2025.100341","url":null,"abstract":"<div><div>The growing reliance on big data frameworks such as Hadoop has revolutionized data processing across various domains, enabling large-scale storage and distributed computation. Hadoop is widely employed in real-world applications such as high-performance computation tasks, e-commerce and data analysis in healthcare. However, the efficiency of Hadoop systems is often hampered by faults and anomalies, with stragglers emerging as one of the most prevalent issues. Stragglers disrupt workflows, waste resources and degrade system performance. While existing anomaly detection models employ methods like median analysis or static thresholds, they often struggle with issues such as high false positives, lack of adaptability and poor handling of complex heterogeneous environments. To address these challenges, this paper presents <span>Plabs</span>, a flexible stragglers detection framework for Hadoop. The framework comprises two core components: (1) a Monitoring Module providing real-time tracking of cluster resources and task progress and (2) a Pluggable AI-based straggler detection module, designed for precise straggler task identification. By leveraging advanced monitoring and AI-driven analysis, <span>Plabs</span> offers an automated, flexible and scalable solution for detecting stragglers at run-time in Hadoop clusters. We evaluated <span>Plabs</span> exhaustively with three Machine Learning (ML), two Deep Learning (DL) and two Large Language Models (LLMs) on five different applications in a real testbed environment. Our experiment evaluation shows that DL models outperform others in identifying Hadoop stragglers, achieving superior accuracy and reliability for all the applications.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100341"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization 边缘个性化的聚类自适应分层联邦学习

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-07-08 DOI: 10.1016/j.hcc.2025.100343

Lihua Song , Jing Li , Honglu Jiang , Shuhua Wei , Yufei Guo

Federated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL) framework, which provides edge-level personalization to effectively overcomes non-IID data and alleviates the overfitting in the personalization process. The three-layer framework makes the learning and personalization process more feasible compared to traditional two-layer federated learning, as edge servers typically offer greater computing power and more efficient communication with the cloud server. Specifically, we use the K-Means++ clustering algorithm to group local clients based on their model updates, ensuring that clients with similar data distributions are clustered together and assigned to the same edge server. Each edge server then generates a personalized model by blending the global model with the edge model, which is adaptively updated and optimized through multiple iterations. Additionally, we introduce a novel aggregation rule on the cloud server to produce a global model with improved performance. Experiments on the MNIST, FMNIST, and KMNIST datasets demonstrate that CHPFL effectively overcomes non-IID data distribution and outperforms HPFL, APFL, and FedALA in non-IID settings.

联邦学习面临着非iid数据分布的挑战，通常会导致使用全局模型的单个客户机的性能不是最优。为了解决这一问题，我们提出了一种聚类分层个性化联邦学习（CHPFL）框架，该框架提供边缘级个性化，有效克服了非iid数据，减轻了个性化过程中的过拟合。与传统的两层联邦学习相比，三层框架使学习和个性化过程更加可行，因为边缘服务器通常提供更强大的计算能力，并与云服务器进行更有效的通信。具体来说，我们使用k - means++聚类算法根据模型更新对本地客户端进行分组，确保具有相似数据分布的客户端聚在一起并分配到相同的边缘服务器。然后，每个边缘服务器通过将全局模型与边缘模型混合生成个性化模型，并通过多次迭代自适应更新和优化该模型。此外，我们在云服务器上引入了一种新的聚合规则，以产生具有改进性能的全局模型。在MNIST、FMNIST和KMNIST数据集上的实验表明，CHPFL有效地克服了非iid数据分布，并且在非iid设置下优于HPFL、APFL和FedALA。

{"title":"CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization","authors":"Lihua Song , Jing Li , Honglu Jiang , Shuhua Wei , Yufei Guo","doi":"10.1016/j.hcc.2025.100343","DOIUrl":"10.1016/j.hcc.2025.100343","url":null,"abstract":"<div><div>Federated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL) framework, which provides edge-level personalization to effectively overcomes non-IID data and alleviates the overfitting in the personalization process. The three-layer framework makes the learning and personalization process more feasible compared to traditional two-layer federated learning, as edge servers typically offer greater computing power and more efficient communication with the cloud server. Specifically, we use the K-Means++ clustering algorithm to group local clients based on their model updates, ensuring that clients with similar data distributions are clustered together and assigned to the same edge server. Each edge server then generates a personalized model by blending the global model with the edge model, which is adaptively updated and optimized through multiple iterations. Additionally, we introduce a novel aggregation rule on the cloud server to produce a global model with improved performance. Experiments on the MNIST, FMNIST, and KMNIST datasets demonstrate that CHPFL effectively overcomes non-IID data distribution and outperforms HPFL, APFL, and FedALA in non-IID settings.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100343"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147394839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

KANs-DETR: Enhancing Detection Transformer with Kolmogorov–Arnold Networks for small object kan - detr：基于Kolmogorov-Arnold网络的小目标增强检测变压器

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-07-01 DOI: 10.1016/j.hcc.2025.100336

Jingyu Zhang , Wentao Peng , Anyan Xiao , Tao Liu , Junchao Fu , Jian Chen , Zhuo Yan

This research proposed an end-to-end object detection network based on Kolmogorov–Arnold Networks (KANs)-Detection Transformer (DETR). KANs block was introduced into encoder–decoder structure instead of the full connection layer to dynamically learn the activation function and improve the robustness and accuracy of the model. Experiments showed that the detection capability of KANs-DETR on multicategory object detection was better than that of HGNetv2 and Swin Transformer as backbone. Furthermore, in order to solve the problem of insensitivity to small objects, the Squeeze-and-Excitation module was applied for feature fusion and presented better performance. The KANs-DETR achieved high detection accuracy and efficiency in handling small objects in complex scenes, providing a new perspective for network optimization.

本研究提出一种基于Kolmogorov-Arnold网络(KANs)-检测变压器（DETR）的端到端目标检测网络。在编解码器结构中引入KANs块代替全连接层，动态学习激活函数，提高模型的鲁棒性和准确性。实验表明，kan - detr对多类目标的检测能力优于HGNetv2和Swin Transformer作为主干的检测能力。此外，为了解决对小物体不敏感的问题，采用了Squeeze-and-Excitation模块进行特征融合，表现出更好的性能。kan - detr在复杂场景中处理小目标时实现了较高的检测精度和效率，为网络优化提供了新的视角。

引用次数: 0

A novel zero-day ransomware detection approach based on CVAE and 1D-CNN 一种基于CVAE和1D-CNN的零日勒索软件检测方法

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-07-01 DOI: 10.1016/j.hcc.2025.100338

Bohan Cui , Yan Hu , Tianheng Qu , Yunhua He , Limin Sun

Ransomware has emerged as one of the most prevalent and destructive cyber attacks confronting global organizations. By locking critical devices or encrypting essential data and then demanding payment for restoration, ransomware attacks disrupt operations, result in significant financial losses, and damage organizational reputations. In particular, zero-day ransomware attacks, which attempt to exploit previously unknown vulnerabilities, pose a severe threat to existing cyber security solutions. Due to the lack of training data, detection of zero-day ransomware attacks remains a significant challenge. This paper proposes a novel zero-day ransomware detection framework that integrates a refined Conditional Variational Autoencoder (CVAE) with a 1D Convolutional Neural Network (1D-CNN). The encoder of the CVAE model comprises a posterior network and a parallel prior network. Using variational coding, the posterior network maps behavioral features of software samples from known families into a latent space, represented by a fixed multivariate Gaussian distribution with a diagonal covariance matrix. Simultaneously, the prior network eliminates dependency on class labels while maintaining distributional consistency with the posterior network via Kullback–Leibler (KL) divergence minimization. This dual-network structure enables unified latent space mapping for both labeled and unlabeled samples, effectively narrowing distributional discrepancies between software samples from known and unknown families. The harmonized latent representations subsequently enhance the discriminative capability of the 1D-CNN classifier in detecting zero-day ransomware. The comprehensive experimental results have verified that the proposed method can effectively detect zero-day ransomware attacks.

勒索软件已经成为全球组织面临的最普遍和最具破坏性的网络攻击之一。通过锁定关键设备或加密重要数据，然后要求支付恢复费用，勒索软件攻击会破坏操作，导致重大财务损失，并损害组织声誉。特别是，零日勒索软件攻击，试图利用以前未知的漏洞，对现有的网络安全解决方案构成严重威胁。由于缺乏训练数据，零日勒索软件攻击的检测仍然是一个重大挑战。本文提出了一种新的零日勒索软件检测框架，该框架集成了改进的条件变分自编码器（CVAE）和一维卷积神经网络（1D- cnn）。CVAE模型的编码器包括一个后验网络和一个并行的先验网络。使用变分编码，后验网络将来自已知家族的软件样本的行为特征映射到一个潜在空间中，该空间由具有对角协方差矩阵的固定多元高斯分布表示。同时，先验网络消除了对类标签的依赖，同时通过Kullback-Leibler （KL）散度最小化保持与后验网络的分布一致性。这种双重网络结构使标记和未标记样本的潜在空间映射统一，有效地缩小了已知和未知家族软件样本之间的分布差异。统一的潜在表征随后增强了1D-CNN分类器检测零日勒索软件的判别能力。综合实验结果验证了该方法能够有效检测零日勒索软件攻击。

{"title":"A novel zero-day ransomware detection approach based on CVAE and 1D-CNN","authors":"Bohan Cui , Yan Hu , Tianheng Qu , Yunhua He , Limin Sun","doi":"10.1016/j.hcc.2025.100338","DOIUrl":"10.1016/j.hcc.2025.100338","url":null,"abstract":"<div><div>Ransomware has emerged as one of the most prevalent and destructive cyber attacks confronting global organizations. By locking critical devices or encrypting essential data and then demanding payment for restoration, ransomware attacks disrupt operations, result in significant financial losses, and damage organizational reputations. In particular, zero-day ransomware attacks, which attempt to exploit previously unknown vulnerabilities, pose a severe threat to existing cyber security solutions. Due to the lack of training data, detection of zero-day ransomware attacks remains a significant challenge. This paper proposes a novel zero-day ransomware detection framework that integrates a refined Conditional Variational Autoencoder (CVAE) with a 1D Convolutional Neural Network (1D-CNN). The encoder of the CVAE model comprises a posterior network and a parallel prior network. Using variational coding, the posterior network maps behavioral features of software samples from known families into a latent space, represented by a fixed multivariate Gaussian distribution with a diagonal covariance matrix. Simultaneously, the prior network eliminates dependency on class labels while maintaining distributional consistency with the posterior network via Kullback–Leibler (KL) divergence minimization. This dual-network structure enables unified latent space mapping for both labeled and unlabeled samples, effectively narrowing distributional discrepancies between software samples from known and unknown families. The harmonized latent representations subsequently enhance the discriminative capability of the 1D-CNN classifier in detecting zero-day ransomware. The comprehensive experimental results have verified that the proposed method can effectively detect zero-day ransomware attacks.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100338"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145618667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Securing educational LLMs: A generalised taxonomy of attacks on LLMs and DREAD risk assessment 保护教育法学硕士：法学硕士攻击的一般分类和恐惧风险评估

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-11-04 DOI: 10.1016/j.hcc.2025.100371

Farzana Zahid , Anjalika Sewwandi , Lee Brandon , Vimal Kumar , Roopak Sinha

Due to perceptions of efficiency and significant productivity gains, various organisations, including in education, are adopting Large Language Models (LLMs) into their workflows. Educator-facing, learner-facing, and institution-facing LLMs, collectively, Educational Large Language Models (eLLMs), complement and enhance the effectiveness of teaching, learning, and academic operations. However, their integration into an educational setting raises significant cybersecurity concerns. A comprehensive landscape of contemporary attacks on LLMs and their impact on the educational environment is missing. This study presents a generalised taxonomy of fifty attacks on LLMs, which are categorised as attacks targeting either models or their infrastructure. The severity of these attacks is evaluated in the educational sector using the DREAD risk assessment framework. Our risk assessment indicates that token smuggling, adversarial prompts, direct injection, and multi-step jailbreak are critical attacks on eLLMs. The proposed taxonomy, its application in the educational environment, and our risk assessment will help academic and industrial practitioners to build resilient solutions that protect learners and institutions.

由于对效率和生产力显著提高的认识，包括教育在内的各种组织正在将大型语言模型（llm）引入其工作流程。面向教育者、面向学习者和面向机构的法学硕士，统称为教育大语言模型（Educational Large Language Models, ellm），它补充并提高了教学、学习和学术运作的有效性。然而，将它们整合到教育环境中引发了重大的网络安全问题。对于法学硕士受到的当代攻击及其对教育环境的影响，我们缺乏一个全面的视角。本研究提出了针对法学硕士的50种攻击的一般分类，这些攻击被归类为针对模型或其基础设施的攻击。这些攻击的严重程度在教育部门使用DREAD风险评估框架进行评估。我们的风险评估表明，令牌走私、对抗性提示、直接注入和多步越狱是对mdm的关键攻击。提出的分类法，其在教育环境中的应用，以及我们的风险评估，将有助于学术和工业从业者建立有弹性的解决方案，保护学习者和机构。

{"title":"Securing educational LLMs: A generalised taxonomy of attacks on LLMs and DREAD risk assessment","authors":"Farzana Zahid , Anjalika Sewwandi , Lee Brandon , Vimal Kumar , Roopak Sinha","doi":"10.1016/j.hcc.2025.100371","DOIUrl":"10.1016/j.hcc.2025.100371","url":null,"abstract":"<div><div>Due to perceptions of efficiency and significant productivity gains, various organisations, including in education, are adopting Large Language Models (LLMs) into their workflows. Educator-facing, learner-facing, and institution-facing LLMs, collectively, Educational Large Language Models (eLLMs), complement and enhance the effectiveness of teaching, learning, and academic operations. However, their integration into an educational setting raises significant cybersecurity concerns. A comprehensive landscape of contemporary attacks on LLMs and their impact on the educational environment is missing. This study presents a generalised taxonomy of fifty attacks on LLMs, which are categorised as attacks targeting either models or their infrastructure. The severity of these attacks is evaluated in the educational sector using the DREAD risk assessment framework. Our risk assessment indicates that token smuggling, adversarial prompts, direct injection, and multi-step jailbreak are critical attacks on eLLMs. The proposed taxonomy, its application in the educational environment, and our risk assessment will help academic and industrial practitioners to build resilient solutions that protect learners and institutions.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100371"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147394842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Is the metaverse really coming to fruition? A survey of applied metaverse and extended reality 超宇宙真的要开花结果了吗？应用元现实与扩展现实综述

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-12-05 DOI: 10.1016/j.hcc.2025.100376

Zhiguo Liu , Yan Huang , Junyu Mai , Wei Li , Zhipeng Cai , Yingshu Li

This survey examines the current state of the Metaverse, encompassing its fundamental concepts, technological framework, practical applications, and user experience to evaluate its stage of development. This paper reviews the core concepts of the Metaverse and Extended Reality (XR) and evaluates the latest advancements in hardware and software technologies. Furthermore, it examines the Metaverse’s typical applications in four key domains: education, training, medicine, and mixed life, while summarizing user feedback to identify its advantages and challenges. The feedback indicates that the Metaverse offers notable benefits, including immersive experiences, enhanced training effectiveness, cost efficiency, and improved safety. However, significant challenges remain, such as hardware performance limitations, software inefficiencies, user discomfort, health risks, and social and ethical concerns. Our analysis suggests that while the Metaverse has yet to reach full maturity, it holds great potential for future development. To further advance the field, this paper highlights key research priorities in artificial intelligence(AI), quantum computing, and social governance, providing insights for future studies.

本调查考察了Metaverse的当前状态，包括其基本概念、技术框架、实际应用和用户体验，以评估其发展阶段。本文回顾了虚拟现实和扩展现实（XR）的核心概念，并对硬件和软件技术的最新进展进行了评估。此外，本文还研究了Metaverse在四个关键领域的典型应用：教育、培训、医学和混合生活，同时总结了用户反馈，以确定其优势和挑战。反馈表明，Metaverse提供了显著的好处，包括身临其境的体验、增强的培训效果、成本效益和安全性。然而，仍然存在重大挑战，例如硬件性能限制、软件效率低下、用户不适、健康风险以及社会和道德问题。我们的分析表明，虽然虚拟宇宙还没有完全成熟，但它在未来的发展中具有巨大的潜力。为了进一步推进这一领域，本文强调了人工智能（AI）、量子计算和社会治理方面的关键研究重点，为未来的研究提供了见解。

{"title":"Is the metaverse really coming to fruition? A survey of applied metaverse and extended reality","authors":"Zhiguo Liu , Yan Huang , Junyu Mai , Wei Li , Zhipeng Cai , Yingshu Li","doi":"10.1016/j.hcc.2025.100376","DOIUrl":"10.1016/j.hcc.2025.100376","url":null,"abstract":"<div><div>This survey examines the current state of the Metaverse, encompassing its fundamental concepts, technological framework, practical applications, and user experience to evaluate its stage of development. This paper reviews the core concepts of the Metaverse and Extended Reality (XR) and evaluates the latest advancements in hardware and software technologies. Furthermore, it examines the Metaverse’s typical applications in four key domains: education, training, medicine, and mixed life, while summarizing user feedback to identify its advantages and challenges. The feedback indicates that the Metaverse offers notable benefits, including immersive experiences, enhanced training effectiveness, cost efficiency, and improved safety. However, significant challenges remain, such as hardware performance limitations, software inefficiencies, user discomfort, health risks, and social and ethical concerns. Our analysis suggests that while the Metaverse has yet to reach full maturity, it holds great potential for future development. To further advance the field, this paper highlights key research priorities in artificial intelligence(AI), quantum computing, and social governance, providing insights for future studies.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100376"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147394843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digital twin and metaverse-enhanced battery management for electric vehicles 电动汽车的数字孪生和metaverse增强电池管理

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-10-14 DOI: 10.1016/j.hcc.2025.100358

Judith Nkechinyere Njoku , Ebuka Chinaechetam Nkoro , Robin Matthew Medina , Paul Michael Custodio , Cosmas Ifeanyi Nwakanma , Jae-Min Lee , Dong-Seong Kim

The Internet of Things (IoT) and cyber–physical systems (CPS) are driving digital transformation and automation. An essential component of CPS is digital twin (DT) technology, which enables real-time synchronization between physical assets and their virtual counterparts. Battery management systems (BMS) in electric vehicles (EVs) face challenges in handling large volumes of sensor data, often leading to reduced accuracy in battery-state estimation. To address these challenges, DTs have been explored to aid real-time diagnosis and monitoring. One critical step toward the success of DTs is to have practical reference architectures. This paper presents proposes a novel six-layer DT architecture tailored for BMS, extending existing CPS/DT-BMS models by integrating high-fidelity electrochemical modeling, robust nonlinear state estimation, and interactive 3D visualization in a Metaverse environment. The architecture is designed with scalability in mind, supporting deployment on lightweight embedded platforms or via cloud-hosted rendering for resource-limited devices. We validate the approach using MATLAB to develop a thermally coupled SPMe-based DT of a lithium-ion NMC battery, synchronized with a virtual battery model in Unreal Engine for immersive visualization. Experimental results demonstrate accurate state-of-charge estimation (RMSE 0.23%) and low-latency real-time monitoring, highlighting the framework’s potential for deployment in large-scale EV BMS applications.

物联网（IoT）和网络物理系统（CPS）正在推动数字化转型和自动化。CPS的一个重要组成部分是数字孪生（DT）技术，它可以实现物理资产和虚拟资产之间的实时同步。电动汽车中的电池管理系统（BMS）在处理大量传感器数据方面面临挑战，通常会导致电池状态估计的准确性降低。为了应对这些挑战，人们探索了DTs来帮助实时诊断和监测。迈向dt成功的关键一步是拥有实用的参考架构。本文提出了一种为BMS量身定制的新型六层DT架构，通过集成高保真电化学建模、鲁棒非线性状态估计和元宇宙环境中的交互式3D可视化，扩展了现有的CPS/DT-BMS模型。该架构在设计时考虑了可伸缩性，支持在轻量级嵌入式平台上进行部署，或者通过云托管呈现资源有限的设备。我们使用MATLAB验证了该方法，开发了一个基于热耦合spme的锂离子NMC电池的DT，并与虚幻引擎中的虚拟电池模型同步，以实现沉浸式可视化。实验结果表明，该框架具有准确的充电状态估计（RMSE 0.23%）和低延迟的实时监控，具有大规模EV BMS应用部署的潜力。

{"title":"Digital twin and metaverse-enhanced battery management for electric vehicles","authors":"Judith Nkechinyere Njoku , Ebuka Chinaechetam Nkoro , Robin Matthew Medina , Paul Michael Custodio , Cosmas Ifeanyi Nwakanma , Jae-Min Lee , Dong-Seong Kim","doi":"10.1016/j.hcc.2025.100358","DOIUrl":"10.1016/j.hcc.2025.100358","url":null,"abstract":"<div><div>The Internet of Things (IoT) and cyber–physical systems (CPS) are driving digital transformation and automation. An essential component of CPS is digital twin (DT) technology, which enables real-time synchronization between physical assets and their virtual counterparts. Battery management systems (BMS) in electric vehicles (EVs) face challenges in handling large volumes of sensor data, often leading to reduced accuracy in battery-state estimation. To address these challenges, DTs have been explored to aid real-time diagnosis and monitoring. One critical step toward the success of DTs is to have practical reference architectures. This paper presents proposes a novel six-layer DT architecture tailored for BMS, extending existing CPS/DT-BMS models by integrating high-fidelity electrochemical modeling, robust nonlinear state estimation, and interactive 3D visualization in a Metaverse environment. The architecture is designed with scalability in mind, supporting deployment on lightweight embedded platforms or via cloud-hosted rendering for resource-limited devices. We validate the approach using MATLAB to develop a thermally coupled SPMe-based DT of a lithium-ion NMC battery, synchronized with a virtual battery model in Unreal Engine for immersive visualization. Experimental results demonstrate accurate state-of-charge estimation (RMSE 0.23%) and low-latency real-time monitoring, highlighting the framework’s potential for deployment in large-scale EV BMS applications.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100358"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147394840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A fast gray-box adversarial example generation algorithm based on FakeBob 基于FakeBob的快速灰盒对抗示例生成算法

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-07-01 DOI: 10.1016/j.hcc.2025.100337

Jia Zheng , Wanjin Hou , Hua Zhang , Ming Lv , Huiyu Zhou

There are the excessive queries to the targeted model during the generates of gray-box adversarial examples for speaker recognition systems, which result in high costs of attacks. In this paper, a fast generates algorithm of gray-box adversarial example is proposed based on FakeBob, named F-FakeBob. This algorithm introduces a threshold mechanism for optimization to the optimization strategy of gradient. Only when the increasing of the confidence scores of the adversarial example before and after optimizing is less than the threshold, the gradient is recalculated for the next iteration. By reducing the frequency of gradient calculations, the number of queries to the targeted system is decreased. Experiments on three public datasets of speech, TIMIT, Common Voice, and Voxceleb2, are conducted to generate adversarial examples. The targeted speaker recognition models are based on ECAPA-TDNN and TitaNet architectures. The experimental results show that F-FakeBob can achieve a targeted attack success rate of 99.2% and the number of queries are effectively reduced in the adversarial example generates, with an average query reduction of 25.71% compared to FakeBob.

针对说话人识别系统，在灰盒对抗示例生成过程中，存在对目标模型查询过多的问题，导致攻击代价高。本文提出了一种基于FakeBob的灰盒对抗样例快速生成算法，命名为F-FakeBob。该算法在梯度优化策略中引入了优化的阈值机制。只有优化前后对抗性样本置信度分数的增量小于阈值时，才会重新计算下一次迭代的梯度。通过减少梯度计算的频率，可以减少对目标系统的查询数量。在三个公共语音数据集TIMIT、Common Voice和Voxceleb2上进行实验，生成对抗性样例。目标说话人识别模型基于ECAPA-TDNN和TitaNet架构。实验结果表明，F-FakeBob可以实现99.2%的目标攻击成功率，并且在生成的对抗性示例中有效减少了查询次数，与FakeBob相比，平均查询次数减少了25.71%。

{"title":"A fast gray-box adversarial example generation algorithm based on FakeBob","authors":"Jia Zheng , Wanjin Hou , Hua Zhang , Ming Lv , Huiyu Zhou","doi":"10.1016/j.hcc.2025.100337","DOIUrl":"10.1016/j.hcc.2025.100337","url":null,"abstract":"<div><div>There are the excessive queries to the targeted model during the generates of gray-box adversarial examples for speaker recognition systems, which result in high costs of attacks. In this paper, a fast generates algorithm of gray-box adversarial example is proposed based on FakeBob, named F-FakeBob. This algorithm introduces a threshold mechanism for optimization to the optimization strategy of gradient. Only when the increasing of the confidence scores of the adversarial example before and after optimizing is less than the threshold, the gradient is recalculated for the next iteration. By reducing the frequency of gradient calculations, the number of queries to the targeted system is decreased. Experiments on three public datasets of speech, TIMIT, Common Voice, and Voxceleb2, are conducted to generate adversarial examples. The targeted speaker recognition models are based on ECAPA-TDNN and TitaNet architectures. The experimental results show that F-FakeBob can achieve a targeted attack success rate of 99.2% and the number of queries are effectively reduced in the adversarial example generates, with an average query reduction of 25.71% compared to FakeBob.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100337"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147394838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A privacy-preserving class imbalance mitigation framework for face recognition 一种保护隐私的人脸识别类失衡缓解框架

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-05-21 DOI: 10.1016/j.hcc.2025.100325

Amani Aldahiri , Ibrahim Khalil , Mohammad Saidur Rahman , Mohammed Atiquzzaman

AI-powered face recognition has become essential to various IoT applications, including home automation, security systems, and personalized services. While these systems offer significant advancements, they still face critical challenges related to accuracy and privacy. One major issue is class imbalance, which is common in face recognition systems where certain demographic groups are underrepresented. This imbalance results in biased models, compromising the accuracy and fairness of these systems. Furthermore, traditional centralized training methods can expose sensitive facial data, raising serious privacy concerns. Federated Learning (FL) has emerged as a solution to improve model training by enabling collaboration across devices without sharing sensitive data. However, it also worsens the issue of data heterogeneity. This paper proposes a Hierarchical Federated Learning (HFL) framework to address class imbalance while preserving privacy. By aggregating local models at different hierarchical levels, the framework mitigates data imbalance and enhances fairness in face recognition systems. Additionally, a privacy-preserving mechanism based on Secure Multi-Party Computation (SMPC) is implemented to ensure data security during the training process.

人工智能面部识别已经成为各种物联网应用的关键，包括家庭自动化、安全系统和个性化服务。虽然这些系统取得了重大进步，但它们仍然面临着与准确性和隐私相关的关键挑战。一个主要问题是阶级不平衡，这在某些人口群体代表性不足的人脸识别系统中很常见。这种不平衡导致了有偏见的模型，损害了这些系统的准确性和公平性。此外，传统的集中式训练方法可能会暴露敏感的面部数据，引发严重的隐私问题。联邦学习（FL）已经成为一种解决方案，通过支持跨设备协作而不共享敏感数据来改进模型训练。然而，它也加剧了数据异构的问题。本文提出了一种层次联邦学习（HFL）框架，在保护隐私的同时解决班级不平衡问题。该框架通过对不同层次的局部模型进行聚合，减轻了数据不平衡，提高了人脸识别系统的公平性。此外，采用基于安全多方计算（SMPC）的隐私保护机制，保证训练过程中的数据安全。

{"title":"A privacy-preserving class imbalance mitigation framework for face recognition","authors":"Amani Aldahiri , Ibrahim Khalil , Mohammad Saidur Rahman , Mohammed Atiquzzaman","doi":"10.1016/j.hcc.2025.100325","DOIUrl":"10.1016/j.hcc.2025.100325","url":null,"abstract":"<div><div>AI-powered face recognition has become essential to various IoT applications, including home automation, security systems, and personalized services. While these systems offer significant advancements, they still face critical challenges related to accuracy and privacy. One major issue is class imbalance, which is common in face recognition systems where certain demographic groups are underrepresented. This imbalance results in biased models, compromising the accuracy and fairness of these systems. Furthermore, traditional centralized training methods can expose sensitive facial data, raising serious privacy concerns. Federated Learning (FL) has emerged as a solution to improve model training by enabling collaboration across devices without sharing sensitive data. However, it also worsens the issue of data heterogeneity. This paper proposes a Hierarchical Federated Learning (HFL) framework to address class imbalance while preserving privacy. By aggregating local models at different hierarchical levels, the framework mitigates data imbalance and enhances fairness in face recognition systems. Additionally, a privacy-preserving mechanism based on Secure Multi-Party Computation (SMPC) is implemented to ensure data security during the training process.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100325"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145555491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Localitycache: Toward efficient straggler tolerance in LRC-coded storage via caching local parity blocks Localitycache：通过缓存本地奇偶校验块，在lrc编码存储中实现高效的离散容错

IF 3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

High-Confidence Computing

Pub Date : 2026-03-01 Epub Date: 2025-07-01 DOI: 10.1016/j.hcc.2025.100339

Ximeng Chen , Si Wu , Yinlong Xu

Modern distributed storage systems increasingly employ Locally Repairable Codes (LRCs) to provide reliable, low-cost data storage with high repair efficiency. However, the presence of stragglers, i.e., nodes that unpredictably slow down, can significantly impact access latency. Traditional approaches for handling stragglers, such as detection, blacklisting, or speculative execution, are often insufficient for efficient straggler tolerance. In this paper, we show how an in-memory caching strategy coupled with LRCs can bypass stragglers without relying on precise straggler detection. We propose LocalityCache, a novel in-memory caching mechanism designed for LRC-coded distributed storage systems, which effectively mitigates the impact of stragglers by caching local parity blocks. We provide theoretical guarantees for LocalityCache and show that caching local parity blocks minimizes the likelihood of encountering stragglers. Additionally, we devise optimized workflows for write, read, and repair operations under LocalityCache to ensure system efficiency. We implement LocalityCache in a distributed key–value store prototype atop Redis. Our extensive testbed evaluations show that LocalityCache can significantly reduce read latency of the baselines by up to 73.6% in the presence of stragglers.

现代分布式存储系统越来越多地采用本地可修复代码（lrc）来提供可靠、低成本和高修复效率的数据存储。但是，离散节点（即不可预测地变慢的节点）的存在会显著影响访问延迟。处理掉队者的传统方法，如检测、列入黑名单或推测执行，通常不足以有效地容忍掉队者。在本文中，我们展示了与lrc相结合的内存缓存策略如何绕过掉队者，而不依赖于精确的掉队者检测。我们提出了LocalityCache，这是一种为lrc编码的分布式存储系统设计的新型内存缓存机制，它通过缓存本地奇偶校验块有效地减轻了离散者的影响。我们为LocalityCache提供了理论保证，并表明缓存本地奇偶校验块可以最大限度地减少遇到掉队者的可能性。此外，我们在LocalityCache下优化了写、读和修复操作的工作流程，以确保系统效率。我们在Redis之上的分布式键值存储原型中实现了LocalityCache。我们广泛的测试平台评估表明，LocalityCache可以显着减少基线的读取延迟，在存在散点的情况下可减少高达73.6%。

{"title":"Localitycache: Toward efficient straggler tolerance in LRC-coded storage via caching local parity blocks","authors":"Ximeng Chen , Si Wu , Yinlong Xu","doi":"10.1016/j.hcc.2025.100339","DOIUrl":"10.1016/j.hcc.2025.100339","url":null,"abstract":"<div><div>Modern distributed storage systems increasingly employ Locally Repairable Codes (LRCs) to provide reliable, low-cost data storage with high repair efficiency. However, the presence of stragglers, i.e., nodes that unpredictably slow down, can significantly impact access latency. Traditional approaches for handling stragglers, such as detection, blacklisting, or speculative execution, are often insufficient for efficient straggler tolerance. In this paper, we show how an in-memory caching strategy coupled with LRCs can bypass stragglers without relying on precise straggler detection. We propose LocalityCache, a novel in-memory caching mechanism designed for LRC-coded distributed storage systems, which effectively mitigates the impact of stragglers by caching local parity blocks. We provide theoretical guarantees for LocalityCache and show that caching local parity blocks minimizes the likelihood of encountering stragglers. Additionally, we devise optimized workflows for write, read, and repair operations under LocalityCache to ensure system efficiency. We implement LocalityCache in a distributed key–value store prototype atop Redis. Our extensive testbed evaluations show that LocalityCache can significantly reduce read latency of the baselines by up to 73.6% in the presence of stragglers.</div></div>","PeriodicalId":100605,"journal":{"name":"High-Confidence Computing","volume":"6 1","pages":"Article 100339"},"PeriodicalIF":3.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145790689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0