Computer Standards & Interfaces最新文献_第6页

State of the art of Agile User Experience: Challenges and solution approaches 敏捷用户体验的现状：挑战和解决方案

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-10-10 DOI: 10.1016/j.csi.2025.104083

Jessica Kollmorgen , Jenny Pilz , Tiago Silva da Silva , Jörg Thomaschewski , Eva-Maria Schön

Context:

In agile environments with pressure due to changing requirements, it is necessary to incorporate user needs into product development to ensure product success. Accordingly, User Experience (UX) methods should be integrated into the agile environment. The nature of the disciplines Agile and UX shows similarities that form a reasonable basis for this, like avoiding false expectations using continuous reviews and reducing late changes and associated costs.

Objective:

Nevertheless, challenges hinder the integration of the disciplines in practice. To support researchers and practitioners, we provide an overview of the development of the Agile UX research field to detect research gaps. Challenges and solution approaches are identified to provide concrete assistance in the integration of Agile and UX.

Methods:

Based on a tertiary review of 30 related work papers, the evolution of the research field and gaps are identified. Then, a secondary systematic literature review of 86 papers is used to examine challenges and solution approaches to the integration of Agile and UX to make recommendations for action.

Results:

28 challenges (e.g., “Interdisciplinary Knowledge”) and 103 solution approaches (e.g., “UserX Stories”) were identified, whereby one challenge can have several solution approaches and vice versa. Furthermore, all challenges were still addressed in recent years (2020-2023) and cannot be considered solved.

Conclusion:

With our results, practitioners can identify solution approaches that may be relevant for internal company challenges and make use of synergies. The numbers of mentions also provide an overview of the research field, which researchers can use to develop further solution approaches and close research gaps.

上下文：在需求变化带来压力的敏捷环境中，有必要将用户需求整合到产品开发中，以确保产品成功。因此，用户体验（UX）方法应该集成到敏捷环境中。敏捷和用户体验这两门学科的本质表现出了相似之处，这些相似之处形成了合理的基础，比如使用持续的审查来避免错误的期望，减少后期的变更和相关的成本。目的：然而，在实践中，挑战阻碍了学科的整合。为了支持研究人员和实践者，我们提供了敏捷用户体验研究领域发展的概述，以发现研究差距。确定了挑战和解决方案方法，以便为敏捷和用户体验的集成提供具体的帮助。方法：在对30篇相关文献进行三级综述的基础上，梳理研究领域的演变和差距。然后，对86篇论文进行了二次系统的文献回顾，以检查敏捷和用户体验集成的挑战和解决方案方法，以提出行动建议。结果：确定了28个挑战（例如，“跨学科知识”）和103个解决方案方法（例如，“UserX故事”），因此一个挑战可以有几个解决方案方法，反之亦然。此外，所有挑战在最近几年（2020-2023年）仍在解决，不能认为已经解决。结论：根据我们的结果，从业者可以确定可能与公司内部挑战相关的解决方案方法，并利用协同效应。提及的数量也提供了研究领域的概述，研究人员可以使用它来开发进一步的解决方案方法并缩小研究差距。

{"title":"State of the art of Agile User Experience: Challenges and solution approaches","authors":"Jessica Kollmorgen , Jenny Pilz , Tiago Silva da Silva , Jörg Thomaschewski , Eva-Maria Schön","doi":"10.1016/j.csi.2025.104083","DOIUrl":"10.1016/j.csi.2025.104083","url":null,"abstract":"<div><h3>Context:</h3><div>In agile environments with pressure due to changing requirements, it is necessary to incorporate user needs into product development to ensure product success. Accordingly, User Experience (UX) methods should be integrated into the agile environment. The nature of the disciplines Agile and UX shows similarities that form a reasonable basis for this, like avoiding false expectations using continuous reviews and reducing late changes and associated costs.</div></div><div><h3>Objective:</h3><div>Nevertheless, challenges hinder the integration of the disciplines in practice. To support researchers and practitioners, we provide an overview of the development of the Agile UX research field to detect research gaps. Challenges and solution approaches are identified to provide concrete assistance in the integration of Agile and UX.</div></div><div><h3>Methods:</h3><div>Based on a tertiary review of 30 related work papers, the evolution of the research field and gaps are identified. Then, a secondary systematic literature review of 86 papers is used to examine challenges and solution approaches to the integration of Agile and UX to make recommendations for action.</div></div><div><h3>Results:</h3><div>28 challenges (e.g., “Interdisciplinary Knowledge”) and 103 solution approaches (e.g., “UserX Stories”) were identified, whereby one challenge can have several solution approaches and vice versa. Furthermore, all challenges were still addressed in recent years (2020-2023) and cannot be considered solved.</div></div><div><h3>Conclusion:</h3><div>With our results, practitioners can identify solution approaches that may be relevant for internal company challenges and make use of synergies. The numbers of mentions also provide an overview of the research field, which researchers can use to develop further solution approaches and close research gaps.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104083"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating agentic risk signalling in trusted research environments: Automating VEX with Agent2Agent protocols and model context protocol (MCP) in SACRO and TREvolution pipelines 在可信的研究环境中集成代理风险信号：在SACRO和TREvolution管道中使用Agent2Agent协议和模型上下文协议（MCP）自动化VEX

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-09-30 DOI: 10.1016/j.csi.2025.104079

Petar Radanliev , Kayvan Atefi , Omar Santos , Carsten Maple

This study presents a framework for automating the generation and validation of machine-readable vulnerability statements, known as Vulnerability-Exploitability Exchange (VEX) artefacts, within secure research environments. The work addresses a critical limitation in existing vulnerability reporting, where static scoring systems often fail to capture whether a flaw is truly exploitable in a specific analytic context. By integrating structured metadata capture, runtime instrumentation, and cryptographically verifiable provenance, the framework classifies vulnerabilities as affected, fixed, or not relevant, supported by machine-readable evidence bundles. The methodology was evaluated using containerised applications seeded with deliberately vulnerable components. Software bill of materials and vulnerability scanners were applied to generate baseline inventories, while reproducibility frameworks validated that results could be independently replicated. Findings demonstrate that automated VEX generation can reduce false positives by distinguishing theoretical from actionable risks, thereby improving security assurance and reproducibility in federated infrastructures. At the same time, the research acknowledges significant challenges. Computational overhead from multi-layered monitoring, dependence on external tools, and the risk of false negatives introduce barriers to adoption. Broader pilot studies across heterogeneous domains and benchmarking on standardised testbeds are required to enhance generalisability. Privacy concerns from extensive runtime monitoring and the need for sustainable maintenance models also demand attention. By combining automation with human oversight and aligning with emerging standards, the study contributes a reproducible, auditable, and context-sensitive approach to vulnerability management. The work provides both a proof-of-concept and a roadmap for refining security practices in sensitive computational environments.

本研究提出了一个框架，用于在安全的研究环境中自动生成和验证机器可读的漏洞声明，称为漏洞利用交换（VEX）工件。这项工作解决了现有漏洞报告中的一个关键限制，其中静态评分系统通常无法捕获一个缺陷在特定的分析上下文中是否真正可利用。通过集成结构化元数据捕获、运行时检测和加密可验证的来源，该框架将漏洞分类为受影响的、固定的或不相关的，由机器可读的证据包支持。该方法是使用带有故意易受攻击组件的容器化应用程序进行评估的。应用软件物料清单和漏洞扫描器生成基线清单，而可重复性框架验证了结果可以独立复制。研究结果表明，自动生成VEX可以通过区分理论风险和可操作风险来减少误报，从而提高联邦基础设施的安全性和可重复性。与此同时，这项研究也承认存在重大挑战。多层监控带来的计算开销、对外部工具的依赖以及假阴性的风险都是采用的障碍。需要更广泛的跨异质领域的试点研究和标准化测试平台的基准测试，以增强通用性。广泛的运行时监控带来的隐私问题以及对可持续维护模型的需求也需要引起注意。通过将自动化与人工监督结合起来，并与新出现的标准保持一致，该研究为漏洞管理提供了一种可重复的、可审计的和上下文敏感的方法。这项工作为在敏感的计算环境中改进安全实践提供了概念验证和路线图。

{"title":"Integrating agentic risk signalling in trusted research environments: Automating VEX with Agent2Agent protocols and model context protocol (MCP) in SACRO and TREvolution pipelines","authors":"Petar Radanliev , Kayvan Atefi , Omar Santos , Carsten Maple","doi":"10.1016/j.csi.2025.104079","DOIUrl":"10.1016/j.csi.2025.104079","url":null,"abstract":"<div><div>This study presents a framework for automating the generation and validation of machine-readable vulnerability statements, known as Vulnerability-Exploitability Exchange (VEX) artefacts, within secure research environments. The work addresses a critical limitation in existing vulnerability reporting, where static scoring systems often fail to capture whether a flaw is truly exploitable in a specific analytic context. By integrating structured metadata capture, runtime instrumentation, and cryptographically verifiable provenance, the framework classifies vulnerabilities as affected, fixed, or not relevant, supported by machine-readable evidence bundles. The methodology was evaluated using containerised applications seeded with deliberately vulnerable components. Software bill of materials and vulnerability scanners were applied to generate baseline inventories, while reproducibility frameworks validated that results could be independently replicated. Findings demonstrate that automated VEX generation can reduce false positives by distinguishing theoretical from actionable risks, thereby improving security assurance and reproducibility in federated infrastructures. At the same time, the research acknowledges significant challenges. Computational overhead from multi-layered monitoring, dependence on external tools, and the risk of false negatives introduce barriers to adoption. Broader pilot studies across heterogeneous domains and benchmarking on standardised testbeds are required to enhance generalisability. Privacy concerns from extensive runtime monitoring and the need for sustainable maintenance models also demand attention. By combining automation with human oversight and aligning with emerging standards, the study contributes a reproducible, auditable, and context-sensitive approach to vulnerability management. The work provides both a proof-of-concept and a roadmap for refining security practices in sensitive computational environments.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104079"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Traceable signatures from lattices 来自格子的可追踪签名

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-11-13 DOI: 10.1016/j.csi.2025.104092

Nam Tran , Khoa Nguyen , Dongxi Liu , Josef Pieprzyk , Willy Susilo

Traceable signatures (Kiayas et al., 2004) is an anonymous digital signature system that extends the tracing power of opening authority in group signatures. There are many known constructions of traceable signatures but all are based on number-theoretical/pairing assumptions. For such reason, they may not be secure in the presence of quantum computers. This work revisits the notion of traceable signatures and presents a lattice-based construction provably secure in the quantum random oracle model (QROM).

可跟踪签名（Kiayas et al., 2004）是一种匿名数字签名系统，它扩展了群签名中开放权限的跟踪能力。有许多已知的可追踪签名结构，但都是基于数字理论/配对假设。因此，在量子计算机的存在下，它们可能不安全。这项工作重新审视了可追踪签名的概念，并提出了一个基于格子的构造，可以证明在量子随机预言模型（QROM）中是安全的。

引用次数: 0

ScaFedCrowd: A secure cross-system anonymous authentication and privacy-preserving task recommendation scheme for federated crowdsourcing ScaFedCrowd：一个安全的跨系统匿名认证和隐私保护任务推荐方案，用于联合众包

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-09-03 DOI: 10.1016/j.csi.2025.104057

Pei Ren , Bo Yang , Yanwei Zhou , Tao Wang , Feng Zhu , Ru Meng

As a prominent area of research in the AI 2.0 era, crowdsourcing has garnered significant attention. Traditional crowdsourcing systems suffer from several drawbacks, including single points of failure, privacy breaches, and isolated resources. The development of decentralized, privacy-preserving federated crowdsourcing systems has consequently emerged as an inevitable trend. However, this shift also introduces new security challenges, such as ensuring participant privacy, enabling rational task recommendations, and establishing inter-system trust. To address these challenges, we propose ScaFedCrowd, a secure cross-system anonymous authentication and privacy-preserving task recommendation scheme for federated crowdsourcing. Our scheme utilizes blockchain with smart contracts as the underlying platform to manage the crowdsourcing process, facilitating secure inter-system collaboration. We propose an intra-system registration and authentication method that uses a trapdoor function and non-interactive zero-knowledge (NIZK) proofs to provide optional anonymity for users. Based on similarity measurement and ElGamal cryptography, our scheme achieves secure cross-system authentication and authorization between servers and workers. Furthermore, task recommendations based on simple hashing intersection technique provide a foundation for cross-system authentication, ensuring privacy while recommending the most suitable tasks for workers. Finally, a secure revocation and tracking mechanism ensures the protection of legitimate rights. Security analysis and simulation results demonstrate that ScaFedCrowd enhances effectiveness, security, and versatility.

众包作为人工智能2.0时代的一个突出研究领域，受到了广泛关注。传统的众包系统有几个缺点，包括单点故障、隐私泄露和孤立的资源。因此，分散的、保护隐私的联合众包系统的发展已成为一种不可避免的趋势。然而，这种转变也带来了新的安全挑战，例如确保参与者隐私、启用合理的任务建议以及建立系统间信任。为了解决这些挑战，我们提出了ScaFedCrowd，一个安全的跨系统匿名认证和隐私保护任务推荐方案，用于联合众包。我们的方案利用区块链和智能合约作为底层平台来管理众包过程，促进安全的系统间协作。我们提出了一种系统内注册和认证方法，该方法使用陷阱门函数和非交互式零知识（NIZK）证明为用户提供可选的匿名性。该方案基于相似度度量和ElGamal加密技术，实现了服务器和工作人员之间的安全跨系统认证和授权。此外，基于简单散列交叉技术的任务推荐为跨系统身份验证提供了基础，在确保隐私的同时为工作人员推荐最适合的任务。最后，安全的撤销和跟踪机制确保了合法权利的保护。安全性分析和仿真结果表明，ScaFedCrowd增强了有效性、安全性和通用性。

{"title":"ScaFedCrowd: A secure cross-system anonymous authentication and privacy-preserving task recommendation scheme for federated crowdsourcing","authors":"Pei Ren , Bo Yang , Yanwei Zhou , Tao Wang , Feng Zhu , Ru Meng","doi":"10.1016/j.csi.2025.104057","DOIUrl":"10.1016/j.csi.2025.104057","url":null,"abstract":"<div><div>As a prominent area of research in the AI 2.0 era, crowdsourcing has garnered significant attention. Traditional crowdsourcing systems suffer from several drawbacks, including single points of failure, privacy breaches, and isolated resources. The development of decentralized, privacy-preserving federated crowdsourcing systems has consequently emerged as an inevitable trend. However, this shift also introduces new security challenges, such as ensuring participant privacy, enabling rational task recommendations, and establishing inter-system trust. To address these challenges, we propose ScaFedCrowd, a secure cross-system anonymous authentication and privacy-preserving task recommendation scheme for federated crowdsourcing. Our scheme utilizes blockchain with smart contracts as the underlying platform to manage the crowdsourcing process, facilitating secure inter-system collaboration. We propose an intra-system registration and authentication method that uses a trapdoor function and non-interactive zero-knowledge (NIZK) proofs to provide optional anonymity for users. Based on similarity measurement and ElGamal cryptography, our scheme achieves secure cross-system authentication and authorization between servers and workers. Furthermore, task recommendations based on simple hashing intersection technique provide a foundation for cross-system authentication, ensuring privacy while recommending the most suitable tasks for workers. Finally, a secure revocation and tracking mechanism ensures the protection of legitimate rights. Security analysis and simulation results demonstrate that ScaFedCrowd enhances effectiveness, security, and versatility.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104057"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

EIVBoost: An efficient and interpretable gradient boosting framework for Vertical Federated Learning EIVBoost：一个用于垂直联邦学习的高效、可解释的梯度增强框架

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-10-16 DOI: 10.1016/j.csi.2025.104082

Lianhai Wang, Xiangyan Kong, Shujiang Xu, Shuhui Zhang, Wei Shao, Qizheng Wang

The rapid growth of internet data and stringent privacy regulations have posed significant challenges to traditional machine learning methods in multi-party collaborative environments due to data silos. In this context, Vertical Federated Learning (VFL) has emerged as a promising solution. Gradient boosting tree-based VFL schemes, in particular, have gained prominence due to their widespread applicability. However, conventional gradient boosting tree models in VFL settings suffer from notable shortcomings, including high communication overhead from frequent interactions, inefficient utilization of computational resources, limited model interpretability, and privacy leakage risks arising from joint modeling. To address these issues, we propose EIVBoost, a novel gradient boosting tree framework. EIVBoost leverages Function Secret Sharing (FSS) to implement a secure comparison protocol, enabling passive parties without labels to generate pseudo-labels through shared functions and train independently, thereby significantly reducing communication overhead and training time while ensuring privacy. Furthermore, through model simplification and rule extraction, EIVBoost aggregates rules from independent models into a globally interpretable decision tree, enhancing model transparency and inference efficiency. Comprehensive security analyses demonstrate that EIVBoost effectively safeguards data privacy. Extensive experiments on real-world datasets confirm that the framework substantially improves training efficiency without compromising model accuracy, offering a robust, secure, and interpretable solution for VFL.

由于数据孤岛，互联网数据的快速增长和严格的隐私法规对多方协作环境中的传统机器学习方法提出了重大挑战。在这种情况下，垂直联邦学习（VFL）作为一种很有前途的解决方案出现了。特别是基于梯度增强树的VFL方案，由于其广泛的适用性而获得了突出的地位。然而，在VFL环境下，传统的梯度增强树模型存在明显的缺点，包括频繁交互带来的高通信开销、计算资源的低效利用、模型可解释性有限以及联合建模带来的隐私泄露风险。为了解决这些问题，我们提出了一种新的梯度增强树框架EIVBoost。EIVBoost利用功能秘密共享（FSS）实现安全的比较协议，使没有标签的被动方能够通过共享函数生成伪标签并独立训练，从而在确保隐私的同时显着减少通信开销和训练时间。此外，EIVBoost通过模型简化和规则提取，将独立模型中的规则聚合到全局可解释的决策树中，提高了模型的透明度和推理效率。综合安全分析表明，EIVBoost有效地保护了数据隐私。在真实世界数据集上的大量实验证实，该框架在不影响模型准确性的情况下大大提高了训练效率，为VFL提供了一个鲁棒、安全和可解释的解决方案。

{"title":"EIVBoost: An efficient and interpretable gradient boosting framework for Vertical Federated Learning","authors":"Lianhai Wang, Xiangyan Kong, Shujiang Xu, Shuhui Zhang, Wei Shao, Qizheng Wang","doi":"10.1016/j.csi.2025.104082","DOIUrl":"10.1016/j.csi.2025.104082","url":null,"abstract":"<div><div>The rapid growth of internet data and stringent privacy regulations have posed significant challenges to traditional machine learning methods in multi-party collaborative environments due to data silos. In this context, Vertical Federated Learning (VFL) has emerged as a promising solution. Gradient boosting tree-based VFL schemes, in particular, have gained prominence due to their widespread applicability. However, conventional gradient boosting tree models in VFL settings suffer from notable shortcomings, including high communication overhead from frequent interactions, inefficient utilization of computational resources, limited model interpretability, and privacy leakage risks arising from joint modeling. To address these issues, we propose EIVBoost, a novel gradient boosting tree framework. EIVBoost leverages Function Secret Sharing (FSS) to implement a secure comparison protocol, enabling passive parties without labels to generate pseudo-labels through shared functions and train independently, thereby significantly reducing communication overhead and training time while ensuring privacy. Furthermore, through model simplification and rule extraction, EIVBoost aggregates rules from independent models into a globally interpretable decision tree, enhancing model transparency and inference efficiency. Comprehensive security analyses demonstrate that EIVBoost effectively safeguards data privacy. Extensive experiments on real-world datasets confirm that the framework substantially improves training efficiency without compromising model accuracy, offering a robust, secure, and interpretable solution for VFL.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104082"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324419","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A security-aware multi-criteria decision-making framework for ordering task mapping techniques in 3D-NoC based MPSoC architectures of IoT 基于3D-NoC的物联网MPSoC架构中排序任务映射技术的安全感知多标准决策框架

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-09-13 DOI: 10.1016/j.csi.2025.104075

Ahmed Abbas Jasim Al-Hchaimi , Yousif Raad Muhsen , Dragan Pamucar , Vladimir Simic

Efficient Task Mapping Techniques (TMTs) play a crucial role in enhancing the security of 3-Dimensional Network-on-Chip-based Multiprocessor Systems-on-Chip (3D-NoC-based MPSoCs) architectures deployed in IoT environments by optimizing resource allocation and minimizing vulnerabilities in communication. However, selecting the secure TMT is a fresh challenge due to the difference in importance of evaluation criteria, data variation among these criteria, trade-offs, and uncertainty. This study aims to determine the secure TMT utilizing the Multicriteria Decision-Making (MCDM) framework. Our methodology is separated into three phases. Firstly, this paper establishes a decision matrix for TMT, considering ten criteria and ten alternatives. Secondly, the Pythagorean Fuzzy Set with Weighted Fuzzy Judgment Matrix (PYS-FWJM) method is proposed to determine the weights of ten evaluation criteria. Moreover, the MULTIMOORA-Borda method is employed to construct the TMT selection model based on ten key alternatives. The criteria weighting results highlight that communication overhead (0.1038), thermal management (0.1021), and cost-effectiveness (0.1029) are the most critical factors influencing TMT selection, emphasizing the importance of efficient data transfer, thermal stability, and resource optimization. The MULTIMOORA-Borda ranking results indicate that Dynamic Voltage and Frequency Scaling (DVFS) ranks as the top TMT, while the Branch-and-Bound is the least effective TMT. The framework's effectiveness and robustness are verified through sensitivity analysis and the Spearman technique. This research offers a structured and scalable evaluation model that enables researchers and practitioners to enhance TMT efficiency while ensuring robust security protection in IoT-driven environments. The outputs of this study contribute to achieving SDG 12 by promoting sustainable IoT.

高效任务映射技术（TMTs）通过优化资源分配和最小化通信漏洞，在提高部署在物联网环境中基于三维片上网络的多处理器片上系统（3d - noc）架构的安全性方面发挥着至关重要的作用。然而，由于评估标准的重要性、这些标准之间的数据变化、权衡和不确定性的差异，选择安全的TMT是一个新的挑战。本研究旨在利用多标准决策（MCDM）框架确定安全的TMT。我们的方法分为三个阶段。首先，本文建立了考虑10个准则和10个备选方案的TMT决策矩阵。其次，提出了带有加权模糊判断矩阵的毕达哥拉斯模糊集（PYS-FWJM）方法来确定十个评价指标的权重。此外，采用MULTIMOORA-Borda方法构建了基于10个关键选项的TMT选择模型。标准加权结果表明，通信开销（0.1038）、热管理（0.1021）和成本效益（0.1029）是影响TMT选择的最关键因素，强调了高效数据传输、热稳定性和资源优化的重要性。MULTIMOORA-Borda排序结果表明，动态电压和频率缩放（DVFS）是最有效的TMT，而分支定界是最无效的TMT。通过灵敏度分析和Spearman技术验证了该框架的有效性和鲁棒性。本研究提供了一个结构化和可扩展的评估模型，使研究人员和从业者能够提高TMT效率，同时确保在物联网驱动的环境中提供强大的安全保护。本研究的成果有助于通过促进可持续物联网实现可持续发展目标12。

{"title":"A security-aware multi-criteria decision-making framework for ordering task mapping techniques in 3D-NoC based MPSoC architectures of IoT","authors":"Ahmed Abbas Jasim Al-Hchaimi , Yousif Raad Muhsen , Dragan Pamucar , Vladimir Simic","doi":"10.1016/j.csi.2025.104075","DOIUrl":"10.1016/j.csi.2025.104075","url":null,"abstract":"<div><div>Efficient Task Mapping Techniques (TMTs) play a crucial role in enhancing the security of 3-Dimensional Network-on-Chip-based Multiprocessor Systems-on-Chip (3D-NoC-based MPSoCs) architectures deployed in IoT environments by optimizing resource allocation and minimizing vulnerabilities in communication. However, selecting the secure TMT is a fresh challenge due to the difference in importance of evaluation criteria, data variation among these criteria, trade-offs, and uncertainty. This study aims to determine the secure TMT utilizing the Multicriteria Decision-Making (MCDM) framework. Our methodology is separated into three phases. Firstly, this paper establishes a decision matrix for TMT, considering ten criteria and ten alternatives. Secondly, the Pythagorean Fuzzy Set with Weighted Fuzzy Judgment Matrix (PYS-FWJM) method is proposed to determine the weights of ten evaluation criteria. Moreover, the MULTIMOORA-Borda method is employed to construct the TMT selection model based on ten key alternatives. The criteria weighting results highlight that communication overhead (0.1038), thermal management (0.1021), and cost-effectiveness (0.1029) are the most critical factors influencing TMT selection, emphasizing the importance of efficient data transfer, thermal stability, and resource optimization. The MULTIMOORA-Borda ranking results indicate that Dynamic Voltage and Frequency Scaling (DVFS) ranks as the top TMT, while the Branch-and-Bound is the least effective TMT. The framework's effectiveness and robustness are verified through sensitivity analysis and the Spearman technique. This research offers a structured and scalable evaluation model that enables researchers and practitioners to enhance TMT efficiency while ensuring robust security protection in IoT-driven environments. The outputs of this study contribute to achieving SDG 12 by promoting sustainable IoT.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104075"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145105867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BcFCKA:Blockchain-based Fair and continuous key agreement for DIDComm in Self-Sovereign Identity BcFCKA：基于区块链的DIDComm自主身份公平连续密钥协议

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-10-17 DOI: 10.1016/j.csi.2025.104085

Mingrui Zhang , Ru Meng , Tao Wang , Yanwei Zhou , Yi Zhao , Bo Yang , Lei Zhang

Self-Sovereign Identity (SSI) is a novel identity management paradigm that empowers entities to control their own identities through agents, without relying on centralized authorities. However, the widely adopted DIDComm framework for secure communication between agents in SSI still faces several critical challenges, such as the lack of perfect forward secrecy, insufficient message loss resilience, and the absence of continuous key updates. To address these issues, we propose a blockchain-based Fair and Continuous Key Agreement (BcFCKA) primitive, which enables agents to perform fair and continuous session key updates, even in the presence of message loss and without relying on any centralized trusted entity. We further present a concrete scheme instantiation, namely BcFCX3DH, and provide both formal and informal analyses to demonstrate that our scheme achieves several security properties (e.g., known-key security and perfect forward secrecy) as well as several design goals (e.g., key pre-storage freedom and message loss resilience). In addition, simulation results show that the proposed scheme establishes the initial session key and performs key updates within only a few milliseconds, demonstrating its practicality.

自我主权身份（Self-Sovereign Identity， SSI）是一种新的身份管理范式，它使实体能够通过代理控制自己的身份，而不依赖于集中的权威机构。然而，广泛采用的用于SSI代理之间安全通信的DIDComm框架仍然面临着几个关键的挑战，例如缺乏完善的前向保密，消息丢失弹性不足，以及缺乏连续的密钥更新。为了解决这些问题，我们提出了一个基于区块链的公平和连续密钥协议（BcFCKA）原语，它使代理能够执行公平和连续的会话密钥更新，即使在存在消息丢失并且不依赖于任何集中的可信实体的情况下。我们进一步提出了一个具体的方案实例，即BcFCX3DH，并提供了正式和非正式的分析来证明我们的方案实现了几个安全属性（例如，已知密钥安全性和完美的前向保密）以及几个设计目标（例如，密钥预存储自由和消息丢失弹性）。此外，仿真结果表明，该方案在几毫秒内建立初始会话密钥并执行密钥更新，证明了该方案的实用性。

{"title":"BcFCKA:Blockchain-based Fair and continuous key agreement for DIDComm in Self-Sovereign Identity","authors":"Mingrui Zhang , Ru Meng , Tao Wang , Yanwei Zhou , Yi Zhao , Bo Yang , Lei Zhang","doi":"10.1016/j.csi.2025.104085","DOIUrl":"10.1016/j.csi.2025.104085","url":null,"abstract":"<div><div>Self-Sovereign Identity (SSI) is a novel identity management paradigm that empowers entities to control their own identities through agents, without relying on centralized authorities. However, the widely adopted DIDComm framework for secure communication between agents in SSI still faces several critical challenges, such as the lack of perfect forward secrecy, insufficient message loss resilience, and the absence of continuous key updates. To address these issues, we propose a blockchain-based Fair and Continuous Key Agreement (BcFCKA) primitive, which enables agents to perform fair and continuous session key updates, even in the presence of message loss and without relying on any centralized trusted entity. We further present a concrete scheme instantiation, namely BcFCX3DH, and provide both formal and informal analyses to demonstrate that our scheme achieves several security properties (e.g., known-key security and perfect forward secrecy) as well as several design goals (e.g., key pre-storage freedom and message loss resilience). In addition, simulation results show that the proposed scheme establishes the initial session key and performs key updates within only a few milliseconds, demonstrating its practicality.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104085"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145361675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Overview of methods to improve execution time in image steganography and watermarking 改进图像隐写和水印执行时间的方法概述

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-08-30 DOI: 10.1016/j.csi.2025.104066

Anna Melman, Kristina Dzhanashia, Oleg Evsutin

The cybersecurity problems remain extremely relevant in the modern world. Every year image steganography and watermarking schemes are proposed that solve the problems of hidden confidential data transfer and image authentication, respectively. The authors attempt to maximize the main embedding indicators, such as capacity, invisibility, and robustness. However, in practice, the time effectiveness of embedding schemes also becomes paramount. Some schemes can provide outstanding embedding quality according to the main embedding indicators but have unsuitable time complexity for real-world applications. Others, on the contrary, aim to satisfy the requirements of real applications, sacrificing the main indicators in the process. Some authors manage to achieve the trade-off between embedding efficiency and algorithm complexity using special measures. Yet, in many works, these solutions are not covered in detail. In this paper, an overview of relevant studies in image steganography and watermarking, the authors of which apply various techniques for speed improvement, is presented. Algorithmic, software, and hardware approaches to improving computation time are analyzed separately, and the most widespread solutions are highlighted. The overview ends with promising research directions for improving the performance of additional information embedding into digital images in the context of execution time.

网络安全问题在现代世界仍然非常重要。每年都会提出图像隐写和水印方案，分别解决隐藏机密数据传输和图像认证问题。作者试图最大化主要嵌入指标，如容量、不可见性和鲁棒性。然而，在实际应用中，嵌入方案的时效性也变得至关重要。根据主要嵌入指标，有些方案可以提供出色的嵌入质量，但对于实际应用来说，时间复杂度不合适。另一些则相反，为了满足实际应用的要求，牺牲了过程中的主要指标。一些作者设法在嵌入效率和算法复杂度之间实现折衷。然而，在许多作品中，这些解决方案并没有详细介绍。本文概述了图像隐写和水印的相关研究，作者们应用了各种技术来提高速度。分别分析了改进计算时间的算法、软件和硬件方法，并强调了最广泛的解决方案。最后概述了在执行时间的背景下提高嵌入到数字图像中的附加信息的性能的有前途的研究方向。

{"title":"Overview of methods to improve execution time in image steganography and watermarking","authors":"Anna Melman, Kristina Dzhanashia, Oleg Evsutin","doi":"10.1016/j.csi.2025.104066","DOIUrl":"10.1016/j.csi.2025.104066","url":null,"abstract":"<div><div>The cybersecurity problems remain extremely relevant in the modern world. Every year image steganography and watermarking schemes are proposed that solve the problems of hidden confidential data transfer and image authentication, respectively. The authors attempt to maximize the main embedding indicators, such as capacity, invisibility, and robustness. However, in practice, the time effectiveness of embedding schemes also becomes paramount. Some schemes can provide outstanding embedding quality according to the main embedding indicators but have unsuitable time complexity for real-world applications. Others, on the contrary, aim to satisfy the requirements of real applications, sacrificing the main indicators in the process. Some authors manage to achieve the trade-off between embedding efficiency and algorithm complexity using special measures. Yet, in many works, these solutions are not covered in detail. In this paper, an overview of relevant studies in image steganography and watermarking, the authors of which apply various techniques for speed improvement, is presented. Algorithmic, software, and hardware approaches to improving computation time are analyzed separately, and the most widespread solutions are highlighted. The overview ends with promising research directions for improving the performance of additional information embedding into digital images in the context of execution time.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104066"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144933213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhanced YOLOv8 model for accurate and real-time remote sensing target detection 增强的YOLOv8模型用于精确和实时的遥感目标检测

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-11-12 DOI: 10.1016/j.csi.2025.104093

Israr Ahmad , Fengjun Shang , Muhammad Faheem

Current remote sensing image object detection algorithms often struggle with false positives, missed targets, and suboptimal accuracy. To address these issues, we propose an improved YOLOv8 network (PIYN) solution achieved through targeted modifications to the YOLOv8 architecture. The backbone of YOLOv8 utilizes a Cross-Stage Partial (CSP) structure that includes two convolutions, called a faster C2f module. Firstly, we infuse the C2f module integrating an Efficient Multi-Scale Attention (EMA) mechanism, which enhances the module's ability to process information across various scales. Secondly, we introduce a Compact Path Aggregation Network (Compact-PAN) structure within the neck of the network, which reduces the computational complexity of the model. Finally, replacing the Complete Intersection over Union (CIoU) loss function with the Weighted Intersection over Union (WIoU) loss refines the model's detection accuracy. Additionally, we applied K-fold cross-validation on the dataset to mitigate overfitting. Experiments using the extensive Dataset for Object Detection in Aerial images (DOTA) and the Dataset for Object Recognition in Optical Remote Sensing Imagery (DIOR) reveal PIYN's effectiveness: there is a 2.43 % and 2.56 % increase in Mean Average Precision (mAP) over YOLOv8, respectively, alongside a 4.49 % reduction in GFLOPs. These results demonstrate PIYN's capability to enhance accuracy while maintaining efficiency and solidify its progressive and practical impact, particularly for smart city applications.

当前的遥感图像目标检测算法经常存在误报、目标缺失和精度不理想等问题。为了解决这些问题，我们提出了一个改进的YOLOv8网络（PIYN）解决方案，通过对YOLOv8架构进行有针对性的修改来实现。YOLOv8的主干采用了包括两个卷积的跨阶段部分（CSP）结构，称为更快的C2f模块。首先，我们在C2f模块中引入了高效多尺度注意（EMA）机制，增强了模块跨尺度处理信息的能力。其次，在网络颈部引入紧凑路径聚合网络（Compact- pan）结构，降低了模型的计算复杂度；最后，用加权交联（加权交联）损失代替完全交联（CIoU）损失函数，提高了模型的检测精度。此外，我们在数据集上应用K-fold交叉验证来减轻过拟合。使用航空图像中物体检测的广泛数据集（DOTA）和光学遥感图像中物体识别的数据集（DIOR）进行的实验显示了PIYN的有效性：与YOLOv8相比，平均精度（mAP）分别提高了2.43%和2.56%，GFLOPs降低了4.49%。这些结果表明，PIYN能够在保持效率的同时提高准确性，并巩固其进步和实际影响，特别是在智慧城市应用中。

{"title":"Enhanced YOLOv8 model for accurate and real-time remote sensing target detection","authors":"Israr Ahmad , Fengjun Shang , Muhammad Faheem","doi":"10.1016/j.csi.2025.104093","DOIUrl":"10.1016/j.csi.2025.104093","url":null,"abstract":"<div><div>Current remote sensing image object detection algorithms often struggle with false positives, missed targets, and suboptimal accuracy. To address these issues, we propose an improved YOLOv8 network (PIYN) solution achieved through targeted modifications to the YOLOv8 architecture. The backbone of YOLOv8 utilizes a Cross-Stage Partial (CSP) structure that includes two convolutions, called a faster C2f module. Firstly, we infuse the C2f module integrating an Efficient Multi-Scale Attention (EMA) mechanism, which enhances the module's ability to process information across various scales. Secondly, we introduce a Compact Path Aggregation Network (Compact-PAN) structure within the neck of the network, which reduces the computational complexity of the model. Finally, replacing the Complete Intersection over Union (CIoU) loss function with the Weighted Intersection over Union (WIoU) loss refines the model's detection accuracy. Additionally, we applied K-fold cross-validation on the dataset to mitigate overfitting. Experiments using the extensive Dataset for Object Detection in Aerial images (DOTA) and the Dataset for Object Recognition in Optical Remote Sensing Imagery (DIOR) reveal PIYN's effectiveness: there is a 2.43 % and 2.56 % increase in Mean Average Precision (mAP) over YOLOv8, respectively, alongside a 4.49 % reduction in GFLOPs. These results demonstrate PIYN's capability to enhance accuracy while maintaining efficiency and solidify its progressive and practical impact, particularly for smart city applications.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104093"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145578670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fluent: Round-efficient secure aggregation for private federated learning Fluent：用于私有联邦学习的高效安全聚合

IF 3.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2026-03-01 Epub Date: 2025-11-12 DOI: 10.1016/j.csi.2025.104096

Xincheng Li , Jianting Ning , Geong Sen Poh , Xinchun Yin , Leo Yu Zhang , Tianwei Zhang

Federated learning (FL) facilitates collaborative training of machine learning models among a large number of clients while safeguarding the privacy of their local datasets. However, FL remains susceptible to vulnerabilities such as privacy inference and inversion attacks. Single-server secure aggregation schemes were proposed to address these threats. Nonetheless, they encounter practical constraints due to their round and communication complexities. This work introduces Fluent, a round-and communication-efficient secure aggregation scheme for private FL. Fluent offers improvements compared to state-of-the-art solutions, i.e., BBGLR (Bell et al., 2020) and Flamingo (Ma et al., 2023): (1) it eliminates the need for iterative handshakes and secret sharing operations by efficiently reusing the shares across multiple training iterations, while maintaining an equivalent level of security assurance as BBGLR and Flamingo; (2) it accomplishes both the consistency check and weight unmasking in one round, thereby reducing the communication complexity. With these constructions, Fluent achieves the fewest communication rounds (i.e., two in the collection phase) in the malicious server setting, in contrast to at least three rounds in BBGLR and Flamingo. This significantly reduces the latency for geographically distributed clients; (3) In addition, a dynamic variant with a participant selection algorithm and multilevel (hierarchical) secret sharing scheme was introduced. It facilitates dynamic client joining, hence enhancing the flexibility and scalability of Fluent. We implemented Fluent and compared it with BBGLR and Flamingo. Experimental results based on the EMNIST dataset show that Fluent achieves significant enhancements in training efficiency. Specifically, Fluent achieves improvements of 6.8

\times

and 2.4

\times

in training time against BBGLR and Flamingo respectively, without compromising accuracy.

联邦学习（FL）促进了大量客户端之间机器学习模型的协作训练，同时保护了本地数据集的隐私。然而，FL仍然容易受到隐私推断和反转攻击等漏洞的影响。针对这些威胁，提出了单服务器安全聚合方案。然而，由于它们的循环和通信复杂性，它们遇到了实际的限制。本工作介绍了Fluent，一种用于私有FL的圆形和通信高效的安全聚合方案。与最先进的解决方案(即BBGLR （Bell等人，2020）和Flamingo （Ma等人，2023）相比，Fluent提供了改进：(1)通过在多个训练迭代中有效地重用共享，消除了迭代握手和秘密共享操作的需要，同时保持了与BBGLR和Flamingo相同的安全保证水平；(2)在一轮内完成一致性检查和权值揭开，降低了通信复杂度。通过这些结构，Fluent在恶意服务器设置中实现了最少的通信轮数（即在收集阶段实现了两轮），而在BBGLR和Flamingo中至少实现了三轮。这大大减少了地理上分布的客户端的延迟；(3)此外，引入了一种具有参与者选择算法和多级（分层）秘密共享方案的动态变体。它促进了动态客户端加入，从而增强了Fluent的灵活性和可扩展性。我们实现了Fluent，并将其与BBGLR和Flamingo进行了比较。基于EMNIST数据集的实验结果表明，Fluent在训练效率上有显著提高。具体来说，在不影响准确率的前提下，Fluent对BBGLR和Flamingo的训练时间分别提高了6.8倍和2.4倍。

{"title":"Fluent: Round-efficient secure aggregation for private federated learning","authors":"Xincheng Li , Jianting Ning , Geong Sen Poh , Xinchun Yin , Leo Yu Zhang , Tianwei Zhang","doi":"10.1016/j.csi.2025.104096","DOIUrl":"10.1016/j.csi.2025.104096","url":null,"abstract":"<div><div>Federated learning (FL) facilitates collaborative training of machine learning models among a large number of clients while safeguarding the privacy of their local datasets. However, FL remains susceptible to vulnerabilities such as privacy inference and inversion attacks. Single-server secure aggregation schemes were proposed to address these threats. Nonetheless, they encounter practical constraints due to their round and communication complexities. This work introduces Fluent, a round-and communication-efficient secure aggregation scheme for private FL. Fluent offers improvements compared to state-of-the-art solutions, i.e., BBGLR (Bell et al., 2020) and Flamingo (Ma et al., 2023): (1) it eliminates the need for iterative handshakes and secret sharing operations by efficiently reusing the shares across multiple training iterations, while maintaining an equivalent level of security assurance as BBGLR and Flamingo; (2) it accomplishes both the consistency check and weight unmasking in one round, thereby reducing the communication complexity. With these constructions, Fluent achieves the fewest communication rounds (i.e., two in the collection phase) in the malicious server setting, in contrast to at least three rounds in BBGLR and Flamingo. This significantly reduces the latency for geographically distributed clients; (3) In addition, a dynamic variant with a participant selection algorithm and multilevel (hierarchical) secret sharing scheme was introduced. It facilitates dynamic client joining, hence enhancing the flexibility and scalability of Fluent. We implemented Fluent and compared it with BBGLR and Flamingo. Experimental results based on the EMNIST dataset show that Fluent achieves significant enhancements in training efficiency. Specifically, Fluent achieves improvements of 6.8<span><math><mo>×</mo></math></span> and 2.4<span><math><mo>×</mo></math></span> in training time against BBGLR and Flamingo respectively, without compromising accuracy.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"96 ","pages":"Article 104096"},"PeriodicalIF":3.1,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145578669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0