Computer Standards & Interfaces最新文献_第10页

Certificateless searchable encryption with cryptographic reverse firewalls for IIoT 无证书可搜索加密与加密反向防火墙用于工业物联网

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-06-19 DOI: 10.1016/j.csi.2025.104034

Mazin Taha , Ting Zhong , Rashad Elhabob , Hu Xiong , Mohammed Amoon , Saru Kumari

Integrating the Industrial Internet of Things (IIoT) and cloud computing is increasingly prevalent in modern business. However, to safeguard data privacy in the cloud server (CS), sensitive information must be encrypted prior to uploading to a CS. The real challenge is searching encrypted data without compromising speed or security. Public Key Encryption with Keyword Search (PEKS) schemes enable the search of ciphertexts without exposing sensitive information. This article introduces a novel Certificateless Searchable Encryption with Cryptographic Reverse Firewalls (CL-SE-CRF). Meanwhile, the proposed scheme addresses the PEKS limitations by removing the requirement for conventional certificate management and addressing concerns related to key escrow. In addition, the security analysis demonstrates that the CL-SE-CRF scheme can prevent and resist keyword guessing attacks (KGA), algorithm substitution attacks (ASA), and chosen keyword attacks (CKA). Furthermore, experimental results demonstrate that the CL-SE-CRF significantly reduces communication and computation costs in the IIoT compared to similar protocols. Therefore, the proposed scheme is helpful for IIoT applications.

工业物联网（IIoT）与云计算的融合在现代商业中越来越普遍。但是，为了保护CS中的数据隐私，敏感信息在上传到CS之前必须进行加密。真正的挑战是在不影响速度或安全性的情况下搜索加密数据。使用关键字搜索（PEKS）方案的公钥加密可以在不暴露敏感信息的情况下搜索密文。本文介绍了一种基于加密反向防火墙（CL-SE-CRF）的新型无证书可搜索加密。同时，提议的方案通过取消对传统证书管理的要求和解决与密钥托管相关的问题来解决PEKS的限制。此外，安全性分析表明，CL-SE-CRF方案可以防止和抵抗关键字猜测攻击（KGA）、算法替代攻击（ASA）和选择关键字攻击（CKA）。此外，实验结果表明，与类似协议相比，CL-SE-CRF显著降低了IIoT中的通信和计算成本。因此，该方案有助于工业物联网的应用。

{"title":"Certificateless searchable encryption with cryptographic reverse firewalls for IIoT","authors":"Mazin Taha , Ting Zhong , Rashad Elhabob , Hu Xiong , Mohammed Amoon , Saru Kumari","doi":"10.1016/j.csi.2025.104034","DOIUrl":"10.1016/j.csi.2025.104034","url":null,"abstract":"<div><div>Integrating the Industrial Internet of Things (IIoT) and cloud computing is increasingly prevalent in modern business. However, to safeguard data privacy in the cloud server (CS), sensitive information must be encrypted prior to uploading to a CS. The real challenge is searching encrypted data without compromising speed or security. Public Key Encryption with Keyword Search (PEKS) schemes enable the search of ciphertexts without exposing sensitive information. This article introduces a novel Certificateless Searchable Encryption with Cryptographic Reverse Firewalls (CL-SE-CRF). Meanwhile, the proposed scheme addresses the PEKS limitations by removing the requirement for conventional certificate management and addressing concerns related to key escrow. In addition, the security analysis demonstrates that the CL-SE-CRF scheme can prevent and resist keyword guessing attacks (KGA), algorithm substitution attacks (ASA), and chosen keyword attacks (CKA). Furthermore, experimental results demonstrate that the CL-SE-CRF significantly reduces communication and computation costs in the IIoT compared to similar protocols. Therefore, the proposed scheme is helpful for IIoT applications.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"95 ","pages":"Article 104034"},"PeriodicalIF":4.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144522219","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

Breaking barriers in healthcare: A secure identity framework for seamless access 打破医疗保健中的障碍：实现无缝访问的安全身份框架

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-06-19 DOI: 10.1016/j.csi.2025.104020

Antonio López Martínez , Montassar Naghmouchi , Maryline Laurent , Joaquín García Alfaro , Manuel Gil Pérez , Antonio Ruiz Martínez

The digitization of healthcare data has heightened concerns about security, privacy, and interoperability. Traditional centralized systems are vulnerable to cyberattacks and data breaches, risking the exposure of sensitive patient information and decreasing trust in digital healthcare services. In addition, healthcare stakeholders use various standards and formats, creating challenges for data sharing and seamless communication. To address these points, this article identifies all the healthcare stakeholders and translates each useful element of a patient’s electronic health record (EHR) into Fast Healthcare Interoperability Resources (FHIR), to propose a complete role-based access control model that specifies which FHIR resources an actor is allowed to access. To validate this role model, three new use cases are defined, in which the various stakeholders interact and access the FHIR resources. Moreover, specific smart contracts are detailed to implement the role model in an automated way and provide a robust access control mechanism within healthcare organizations. The feasibility of the proposed access control mechanism is demonstrated through proof-of-concept and test performance measurements. Finally, the solution is validated as a realistic solution adapted to the scale of a country based on health statistics.

医疗保健数据的数字化加剧了人们对安全性、隐私性和互操作性的担忧。传统的集中式系统容易受到网络攻击和数据泄露，可能会暴露敏感的患者信息，并降低对数字医疗保健服务的信任。此外，医疗保健利益相关者使用各种标准和格式，这给数据共享和无缝通信带来了挑战。为了解决这些问题，本文确定了所有医疗保健涉众，并将患者电子健康记录（EHR）的每个有用元素转换为快速医疗保健互操作性资源（FHIR），以提出一个完整的基于角色的访问控制模型，该模型指定参与者可以访问哪些FHIR资源。为了验证这个角色模型，定义了三个新的用例，在这些用例中，各种涉众进行交互并访问FHIR资源。此外，还详细介绍了以自动化方式实现角色模型的特定智能合约，并在医疗保健组织内提供健壮的访问控制机制。通过概念验证和测试性能测量证明了所提出的访问控制机制的可行性。最后，根据卫生统计，验证该解决方案是适合一个国家规模的现实解决方案。

{"title":"Breaking barriers in healthcare: A secure identity framework for seamless access","authors":"Antonio López Martínez , Montassar Naghmouchi , Maryline Laurent , Joaquín García Alfaro , Manuel Gil Pérez , Antonio Ruiz Martínez","doi":"10.1016/j.csi.2025.104020","DOIUrl":"10.1016/j.csi.2025.104020","url":null,"abstract":"<div><div>The digitization of healthcare data has heightened concerns about security, privacy, and interoperability. Traditional centralized systems are vulnerable to cyberattacks and data breaches, risking the exposure of sensitive patient information and decreasing trust in digital healthcare services. In addition, healthcare stakeholders use various standards and formats, creating challenges for data sharing and seamless communication. To address these points, this article identifies all the healthcare stakeholders and translates each useful element of a patient’s electronic health record (EHR) into Fast Healthcare Interoperability Resources (FHIR), to propose a complete role-based access control model that specifies which FHIR resources an actor is allowed to access. To validate this role model, three new use cases are defined, in which the various stakeholders interact and access the FHIR resources. Moreover, specific smart contracts are detailed to implement the role model in an automated way and provide a robust access control mechanism within healthcare organizations. The feasibility of the proposed access control mechanism is demonstrated through proof-of-concept and test performance measurements. Finally, the solution is validated as a realistic solution adapted to the scale of a country based on health statistics.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"95 ","pages":"Article 104020"},"PeriodicalIF":4.1,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144470925","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

Blockchain-aided secure and fair multi-view data outsourcing computation scheme 区块链辅助安全公平的多视图数据外包计算方案

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-06-18 DOI: 10.1016/j.csi.2025.104029

Xinrong Sun , Fanyu Kong , Yunting Tao , Pengyu Cui , Guoyan Zhang , Chunpeng Ge , Baodong Qin

With the widespread deployment of smart sensors, multi-view data has been widely used. Accordingly, multi-view processing algorithms are increasingly researched, among which the cluster-weighted kernel k-means method is an effective approach to dig up information of different views. However, large-scale multi-view data make it difficult to conduct processing algorithms. Therefore, outsourcing complex computations to servers based on privacy-preserving techniques is an effective solution that enables efficient multi-view data analysis. In previous secure outsourcing schemes, the efficiency of the outsourcing process and the fairness of outsourcing transactions are still challenging issues that have not been addressed. In this paper, we propose a blockchain-aided secure and fair multi-view data outsourcing computation scheme. We present an efficient matrix encryption method utilizing a novel secret key matrix to complete cluster-weighted kernel k-means algorithm securely. Different from previous works, we first apply the sparse symmetric orthogonal matrix to encrypt and decrypt sensitive data matrices, which avoids inverse or transposed secret key matrix computation and enhances the efficiency of the outsourcing process. Additionally, we introduce smart contracts to achieve fair outsourcing transactions aided by blockchain. We verify the returned result with the assistance of verifiers based on encrypted data, which improves the efficiency and security of outsourcing transactions. The experimental results indicate that our scheme is 4.72% to 8.52% superior to the state-of-the-art matrix outsourcing computation schemes and achieves 55.79% to 91.95% efficiency improvement compared to the original multi-view data processing method.

随着智能传感器的广泛部署，多视图数据得到了广泛的应用。因此，对多视图处理算法的研究越来越多，其中聚类加权核k-均值法是挖掘不同视图信息的有效方法。然而，大规模的多视图数据给处理算法带来了困难。因此，基于隐私保护技术将复杂的计算外包给服务器是一种有效的解决方案，可以实现高效的多视图数据分析。在以往的安全外判计划中，外判程序的效率和外判交易的公平性仍是未有解决的挑战性问题。本文提出了一种区块链辅助的安全、公平的多视图数据外包计算方案。提出了一种有效的矩阵加密方法，利用一种新的密钥矩阵来安全地完成聚类加权核k-均值算法。与以往不同的是，我们首先采用稀疏对称正交矩阵对敏感数据矩阵进行加密解密，避免了密钥矩阵的逆或转置计算，提高了外包过程的效率。此外，我们引入智能合约，在b区块链的帮助下实现公平的外包交易。我们基于加密数据在验证器的协助下对返回结果进行验证，提高了外包交易的效率和安全性。实验结果表明，该方案比目前最先进的矩阵外包计算方案效率提高4.72% ~ 8.52%，比原多视图数据处理方法效率提高55.79% ~ 91.95%。

{"title":"Blockchain-aided secure and fair multi-view data outsourcing computation scheme","authors":"Xinrong Sun , Fanyu Kong , Yunting Tao , Pengyu Cui , Guoyan Zhang , Chunpeng Ge , Baodong Qin","doi":"10.1016/j.csi.2025.104029","DOIUrl":"10.1016/j.csi.2025.104029","url":null,"abstract":"<div><div>With the widespread deployment of smart sensors, multi-view data has been widely used. Accordingly, multi-view processing algorithms are increasingly researched, among which the cluster-weighted kernel k-means method is an effective approach to dig up information of different views. However, large-scale multi-view data make it difficult to conduct processing algorithms. Therefore, outsourcing complex computations to servers based on privacy-preserving techniques is an effective solution that enables efficient multi-view data analysis. In previous secure outsourcing schemes, the efficiency of the outsourcing process and the fairness of outsourcing transactions are still challenging issues that have not been addressed. In this paper, we propose a blockchain-aided secure and fair multi-view data outsourcing computation scheme. We present an efficient matrix encryption method utilizing a novel secret key matrix to complete cluster-weighted kernel k-means algorithm securely. Different from previous works, we first apply the sparse symmetric orthogonal matrix to encrypt and decrypt sensitive data matrices, which avoids inverse or transposed secret key matrix computation and enhances the efficiency of the outsourcing process. Additionally, we introduce smart contracts to achieve fair outsourcing transactions aided by blockchain. We verify the returned result with the assistance of verifiers based on encrypted data, which improves the efficiency and security of outsourcing transactions. The experimental results indicate that our scheme is 4.72% to 8.52% superior to the state-of-the-art matrix outsourcing computation schemes and achieves 55.79% to 91.95% efficiency improvement compared to the original multi-view data processing method.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"95 ","pages":"Article 104029"},"PeriodicalIF":4.1,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144470974","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

Fuzzy Password Authentication Key Exchange protocol in universal composable framework for blockchain privacy protection b区块链隐私保护通用可组合框架中的模糊密码认证密钥交换协议

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-06-16 DOI: 10.1016/j.csi.2025.104032

Qihong Chen, Changgen Peng, Dequan Xu

In this paper, we construct a lattice-based fuzzy Password Authentication Key Exchange protocol in universal composable model. Through the known Password Authentication Key Exchange scheme, the Randomized Fuzzy Equality protocol and the Oblivious Transfer protocol are introduced to improve Password Authentication Key Exchange into fuzzy Password Authentication Key Exchange. First, the parties go through two rounds of Oblivious Transfer protocol, and then the key exchange is achieved based on the information exchanged. fuzzy Password Authentication Key Exchange satisfies that even if there is noise in the passwords between users, key exchange is still possible. Therefore, fuzzy Password Authentication Key Exchange is suitable for more application scenarios compared to Password Authentication Key Exchange, and the construction is universal composable security.

本文在通用可组合模型下构造了一个基于格的模糊密码认证密钥交换协议。通过已知的密码认证密钥交换方案，引入随机模糊等式协议和遗忘传输协议，将密码认证密钥交换改进为模糊密码认证密钥交换。首先，双方经过两轮的遗忘传输协议，然后根据交换的信息进行密钥交换。模糊密码认证密钥交换满足即使用户之间的密码存在噪声，密钥交换仍然是可能的。因此，相对于密码认证密钥交换，模糊密码认证密钥交换适用于更多的应用场景，并且构建了通用的组合安全。

引用次数: 0

Can a conventional email phishing nudge help fight SMiShing attacks? 传统的电子邮件网络钓鱼能帮助打击钓鱼攻击吗？

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-06-03 DOI: 10.1016/j.csi.2025.104031

Morgan E. Edwards , Jing Chen , Jeremiah D. Still

Phishing attacks, a common cybersecurity threat, aim to deceive end-users into revealing sensitive information. While Human Factors researchers have extensively examined phishing in the email vector, the emergence of phishing in the SMS vector, known as SMiShing, has presented a new challenge. This study breaks new ground by investigating whether a conventional behavioral nudge intervention designed to combat email phishing can be effectively applied to SMiShing. A reflective nudge was implemented, providing participants with a message to encourage appropriate behavior. They were then tasked to sort email and text messages based on legitimacy. We manipulated the presence of nudge (present or absent) and the platform (email or text). Participants’ performance was measured using Signal Detection Theory, and they were asked to provide confidence ratings for each legitimacy decision. Our key findings revealed that the conventional nudge improved performance for email decisions, although it decreased user confidence. For text messages, the nudge hindered participants’ discrimination ability and did not significantly influence response bias performance or confidence ratings. Unfortunately, the effectiveness of the nudge did not simply transfer to text messages. We reflect on how to redesign the conventional nudge to increase its effectiveness against SMiShing.

网络钓鱼攻击是一种常见的网络安全威胁，其目的是欺骗最终用户泄露敏感信息。虽然人为因素研究人员已经广泛研究了电子邮件向量中的网络钓鱼，但短信向量中的网络钓鱼（称为SMiShing）的出现提出了新的挑战。这项研究开辟了新的领域，调查了传统的行为助推干预是否可以有效地用于打击电子邮件网络钓鱼。实施了反思性的推动，为参与者提供了鼓励适当行为的信息。然后，他们被要求根据合法性对电子邮件和短信进行分类。我们操纵了微推的存在（在场或不在场）和平台（电子邮件或文本）。参与者的表现是用信号检测理论来衡量的，他们被要求为每个合法性决定提供信心评级。我们的主要发现表明，传统的轻推提高了电子邮件决策的性能，尽管它降低了用户的信心。对于短信，轻推阻碍了参与者的辨别能力，并没有显著影响反应偏差表现或信心评级。不幸的是，轻推的效果并不仅仅体现在短信上。我们反思如何重新设计传统的轻推，以提高其对SMiShing的有效性。

{"title":"Can a conventional email phishing nudge help fight SMiShing attacks?","authors":"Morgan E. Edwards , Jing Chen , Jeremiah D. Still","doi":"10.1016/j.csi.2025.104031","DOIUrl":"10.1016/j.csi.2025.104031","url":null,"abstract":"<div><div>Phishing attacks, a common cybersecurity threat, aim to deceive end-users into revealing sensitive information. While Human Factors researchers have extensively examined phishing in the email vector, the emergence of phishing in the SMS vector, known as SMiShing, has presented a new challenge. This study breaks new ground by investigating whether a conventional behavioral nudge intervention designed to combat email phishing can be effectively applied to SMiShing. A reflective nudge was implemented, providing participants with a message to encourage appropriate behavior. They were then tasked to sort email and text messages based on legitimacy. We manipulated the presence of nudge (present or absent) and the platform (email or text). Participants’ performance was measured using Signal Detection Theory, and they were asked to provide confidence ratings for each legitimacy decision. Our key findings revealed that the conventional nudge improved performance for email decisions, although it decreased user confidence. For text messages, the nudge hindered participants’ discrimination ability and did not significantly influence response bias performance or confidence ratings. Unfortunately, the effectiveness of the nudge did not simply transfer to text messages. We reflect on how to redesign the conventional nudge to increase its effectiveness against SMiShing.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"95 ","pages":"Article 104031"},"PeriodicalIF":4.1,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144255459","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

Software defect prediction using graph sample and aggregate-attention network optimized with nomadic people optimizer for enhancing the software reliability 利用图样本进行软件缺陷预测，利用游民优化器优化集中注意力网络，提高软件可靠性

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-06-03 DOI: 10.1016/j.csi.2025.104033

P. Dhavakumar , S. Vengadeswaran

The major objective of Software Defect Prediction (SDP) is to detect code location where errors are likely to occur to focus testing efforts on more suspect areas. Therefore, a high-quality software is developed that takes lesser time without effort. The dataset used for SDP usually contains more non-defective examples than defective examples. SDP is an important activity in software engineering that detect potential defects in software systems before they occur. For that, this paper proposes a Software Defect Prediction using Graph Sample and Aggregate-Attention Network optimized with Nomadic people Optimizer for enhancing the Software Reliability (graphSAGE-NPO-SDP). Here, the data are taken from Promise Repository dataset and given to the pre-processing. The pre-processing is done by normalization techniques of Min-Max Scaling. After preprocessing, the features are selected under Univariate Ensemble Feature Selection technique (UEFST). The classification process is performed by graphSAGE. The classification results are classified as defect class and non-defective class. The performance metrics, like Accuracy, Execution time, F-measure, Precision, Root Mean Square Error, Sensitivity, and Specificity is examined. The proposed graphSAGE-NPO-SDP method attains higher accuracy 32.45 %, 36.48 % and 28.34 % when compared to the existing models: Complexity-based over sampling technique in SDP (COT-ACI-SDP), Classification Method for SDP utilizing multiple filter feature selection approach (MLP-SDP), Boosted WOA-SDP and hybrid model depending on deep neural network based for SDP under Software Metrics (DNN-GA-SDP) respectively.

软件缺陷预测（SDP）的主要目标是检测可能发生错误的代码位置，从而将测试工作集中在更可疑的区域。因此，开发一个高质量的软件需要更少的时间和精力。用于SDP的数据集通常包含比缺陷样本更多的非缺陷样本。SDP是软件工程中的一项重要活动，它可以在软件系统中潜在的缺陷发生之前检测出来。为此，本文提出了一种基于图样本和游牧民族优化器优化的聚集注意网络的软件缺陷预测方法，以提高软件可靠性（graphSAGE-NPO-SDP）。在这里，数据取自Promise Repository数据集并交给预处理。预处理采用最小-最大缩放归一化技术。预处理后，采用单变量集成特征选择技术（Univariate Ensemble Feature Selection technique， UEFST）选择特征。分类过程由graphSAGE执行。分类结果分为缺陷类和非缺陷类。性能指标，如准确性，执行时间，f测量，精度，均方根误差，灵敏度和特异性进行检查。本文提出的graphsag - npo -SDP方法与现有的基于复杂度的SDP过采样技术（cots - aci -SDP）、基于多滤波器特征选择方法的SDP分类方法（MLP-SDP）、基于深度神经网络的基于软件度量的SDP混合模型（DNN-GA-SDP）相比，准确率分别达到了32.45%、36.48%和28.34%。

{"title":"Software defect prediction using graph sample and aggregate-attention network optimized with nomadic people optimizer for enhancing the software reliability","authors":"P. Dhavakumar , S. Vengadeswaran","doi":"10.1016/j.csi.2025.104033","DOIUrl":"10.1016/j.csi.2025.104033","url":null,"abstract":"<div><div>The major objective of Software Defect Prediction (SDP) is to detect code location where errors are likely to occur to focus testing efforts on more suspect areas. Therefore, a high-quality software is developed that takes lesser time without effort. The dataset used for SDP usually contains more non-defective examples than defective examples. SDP is an important activity in software engineering that detect potential defects in software systems before they occur. For that, this paper proposes a Software Defect Prediction using Graph Sample and Aggregate-Attention Network optimized with Nomadic people Optimizer for enhancing the Software Reliability (graphSAGE-NPO-SDP). Here, the data are taken from Promise Repository dataset and given to the pre-processing. The pre-processing is done by normalization techniques of Min-Max Scaling. After preprocessing, the features are selected under Univariate Ensemble Feature Selection technique (UEFST). The classification process is performed by graphSAGE. The classification results are classified as defect class and non-defective class. The performance metrics, like Accuracy, Execution time, F-measure, Precision, Root Mean Square Error, Sensitivity, and Specificity is examined. The proposed graphSAGE-NPO-SDP method attains higher accuracy 32.45 %, 36.48 % and 28.34 % when compared to the existing models: Complexity-based over sampling technique in SDP (COT-ACI-SDP), Classification Method for SDP utilizing multiple filter feature selection approach (MLP-SDP), Boosted WOA-SDP and hybrid model depending on deep neural network based for SDP under Software Metrics (DNN-GA-SDP) respectively.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"95 ","pages":"Article 104033"},"PeriodicalIF":4.1,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144262586","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

FedSam: Enhancing federated learning accuracy with differential privacy and data heterogeneity mitigation FedSam：通过差异隐私和数据异构缓解来增强联邦学习的准确性

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-05-28 DOI: 10.1016/j.csi.2025.104019

Hongtao Li , Xinyu Li , Ximeng Liu , Bo Wang , Jie Wang , Youliang Tian

A large-scale model is typically trained on an extensive dataset to update its parameters and enhance its classification capabilities. However, directly using such data can raise significant privacy concerns, especially in the medical field, where datasets often contain sensitive patient information. Federated Learning (FL) offers a solution by enabling multiple parties to collaboratively train a high-performance model without sharing their raw data. Despite this, during the federated training process, attackers can still potentially extract private information from local models. To bolster privacy protections, Differential Privacy (DP) has been introduced to FL, providing stringent safeguards. However, the combination of DP and data heterogeneity can often lead to reduced model accuracy. To tackle these challenges, we introduce a sampling-memory mechanism, FedSam, which improves the accuracy of the global model while maintaining the required noise levels for differential privacy. This mechanism also mitigates the adverse effects of data heterogeneity in heterogeneous federated environments, thereby improving the global model’s overall performance. Experimental evaluations on datasets demonstrate the superiority of our approach. FedSam achieves a classification accuracy of 95.03%, significantly outperforming traditional DP-FedAvg (91.74%) under the same privacy constraints, highlighting FedSam’s robustness and efficiency.

大规模模型通常是在广泛的数据集上进行训练，以更新其参数并增强其分类能力。然而，直接使用这些数据可能会引起严重的隐私问题，特别是在医疗领域，因为数据集通常包含敏感的患者信息。联邦学习（FL）提供了一种解决方案，允许多方在不共享原始数据的情况下协作训练高性能模型。尽管如此，在联合训练过程中，攻击者仍然可能从本地模型中提取私有信息。为了加强隐私保护，差分隐私（DP）被引入到FL，提供严格的保护。然而，DP和数据异质性的结合往往会导致模型精度的降低。为了应对这些挑战，我们引入了一种采样-记忆机制，FedSam，它提高了全局模型的准确性，同时保持了差分隐私所需的噪声水平。该机制还减轻了异构联邦环境中数据异构的不利影响，从而提高了全局模型的整体性能。数据集的实验评估证明了我们方法的优越性。在相同的隐私约束下，FedSam的分类准确率达到95.03%，显著优于传统的dp - fedag(91.74%)，突出了FedSam的鲁棒性和效率。

{"title":"FedSam: Enhancing federated learning accuracy with differential privacy and data heterogeneity mitigation","authors":"Hongtao Li , Xinyu Li , Ximeng Liu , Bo Wang , Jie Wang , Youliang Tian","doi":"10.1016/j.csi.2025.104019","DOIUrl":"10.1016/j.csi.2025.104019","url":null,"abstract":"<div><div>A large-scale model is typically trained on an extensive dataset to update its parameters and enhance its classification capabilities. However, directly using such data can raise significant privacy concerns, especially in the medical field, where datasets often contain sensitive patient information. Federated Learning (FL) offers a solution by enabling multiple parties to collaboratively train a high-performance model without sharing their raw data. Despite this, during the federated training process, attackers can still potentially extract private information from local models. To bolster privacy protections, Differential Privacy (DP) has been introduced to FL, providing stringent safeguards. However, the combination of DP and data heterogeneity can often lead to reduced model accuracy. To tackle these challenges, we introduce a sampling-memory mechanism, FedSam, which improves the accuracy of the global model while maintaining the required noise levels for differential privacy. This mechanism also mitigates the adverse effects of data heterogeneity in heterogeneous federated environments, thereby improving the global model’s overall performance. Experimental evaluations on datasets demonstrate the superiority of our approach. FedSam achieves a classification accuracy of 95.03%, significantly outperforming traditional DP-FedAvg (91.74%) under the same privacy constraints, highlighting FedSam’s robustness and efficiency.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"95 ","pages":"Article 104019"},"PeriodicalIF":4.1,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144177794","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

FEMT-FL: A novel flexible energy management technique using federated learning for energy management in IoT-based distributed green computing systems FEMT-FL：在基于物联网的分布式绿色计算系统中使用联邦学习进行能源管理的一种新型灵活能源管理技术

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-05-08 DOI: 10.1016/j.csi.2025.104017

Jaikumar R , Arun Sekar Rajasekaran , M.V. Nageswara Rao , Anand Nayyar

Green Computing systems bank on sustainable energy sources for service management and request processing. The Internet of Things (IoT) assimilates such computing systems for resource sharing and service distribution. For providing optimized energy balancing and effective utilization of available energy, this research paper proposes a novel flexible energy management technique using federated learning i.e., (FEMT-FT) for reliable energy management between the computing IoT nodes. The equivalent energy management process verifies the energy availability for request processing whereas the reliable energy part identifies the terminating interval to replace the communicating devices. For this purpose, the computing devices' draining and required energy levels are identified in all the request processing and service disseminating instances. The learning trains different energy balancing models that achieve a better service dissemination ratio. In this method, interval termination and new interval allocations are continuous to maximize service dissemination and novel request processing. For the varying requests, the proposed method achieves 8.92 %, 12.31 %, and 8.55 % high service dissemination, energy conservation, and request processing rate respectively.

绿色计算系统以可持续能源为基础进行服务管理和请求处理。物联网（Internet of Things, IoT）吸收了这样的计算系统，用于资源共享和服务分配。为了提供优化的能量平衡和有效利用可用能量，本研究提出了一种新的灵活的能量管理技术，使用联邦学习即（FEMT-FT）在计算物联网节点之间进行可靠的能量管理。等效能量管理过程验证请求处理的能量可用性，而可靠能量部分识别替换通信设备的终止间隔。为此，在所有请求处理和服务传播实例中确定计算设备的消耗和所需的能量水平。学习训练不同的能量平衡模型，以达到更好的服务传播率。在该方法中，区间终止和新区间分配是连续的，以最大限度地提高服务的传播和新请求的处理。对于不同的请求，该方法的服务分发率、节能率和请求处理率分别达到8.92%、12.31%和8.55%。

{"title":"FEMT-FL: A novel flexible energy management technique using federated learning for energy management in IoT-based distributed green computing systems","authors":"Jaikumar R , Arun Sekar Rajasekaran , M.V. Nageswara Rao , Anand Nayyar","doi":"10.1016/j.csi.2025.104017","DOIUrl":"10.1016/j.csi.2025.104017","url":null,"abstract":"<div><div>Green Computing systems bank on sustainable energy sources for service management and request processing. The Internet of Things (IoT) assimilates such computing systems for resource sharing and service distribution. For providing optimized energy balancing and effective utilization of available energy, this research paper proposes a novel flexible energy management technique using federated learning i.e., (FEMT-FT) for reliable energy management between the computing IoT nodes. The equivalent energy management process verifies the energy availability for request processing whereas the reliable energy part identifies the terminating interval to replace the communicating devices. For this purpose, the computing devices' draining and required energy levels are identified in all the request processing and service disseminating instances. The learning trains different energy balancing models that achieve a better service dissemination ratio. In this method, interval termination and new interval allocations are continuous to maximize service dissemination and novel request processing. For the varying requests, the proposed method achieves 8.92 %, 12.31 %, and 8.55 % high service dissemination, energy conservation, and request processing rate respectively.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"94 ","pages":"Article 104017"},"PeriodicalIF":4.1,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143948945","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

Efficient public key authenticated searchable encryption scheme without bilinear pairings 无双线性对的高效公钥认证可搜索加密方案

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-05-05 DOI: 10.1016/j.csi.2025.104016

Meijuan Huang , Jingjie Gan , Bo Yang , Hongzhen Du , Yanqi Zhao

The issue of searching for data within ciphertext files in cloud storage is effectively resolved through public key encryption with keyword search (PEKS). The main security problem it has is the internal keyword guessing attack (IKGA), for which Huang et al. proposed a novel scheme, public key authenticated encryption with keyword search (PAEKS), which employs a combination of encryption and authentication to enhance the security of the scheme. Most PAEKS algorithms utilize bilinear pairings, which are inherently costly from a computational perspective and also offer only single-keyword ciphertext security guarantees. In light of the aforementioned considerations, this paper presents a PAEKS scheme that does not employ bilinear pairings. The scheme is demonstrated to satisfy the criteria of multi-ciphertext and multi-trapdoor security, based on the DDH assumption. Furthermore, the parallel search method is employed during the search phase with the objective of enhancing the overall efficiency of the search process. Ultimately, the experimental results demonstrate that the computational time of the proposed scheme is reduced by a factor of 7 to 28 compared to other schemes using bilinear pairings, and our scheme has higher search efficiency and is more suitable for practical applications.

通过使用关键字搜索（PEKS）对公钥进行加密，有效地解决了云存储中密文文件中数据的搜索问题。其存在的主要安全问题是内部关键字猜测攻击（IKGA），对此Huang等人提出了一种新的方案——公钥认证加密与关键字搜索（PAEKS），该方案采用加密与认证相结合的方式来提高方案的安全性。大多数PAEKS算法使用双线性配对，从计算的角度来看，这本身是昂贵的，并且只提供单关键字密文安全保证。鉴于上述考虑，本文提出了一种不采用双线性配对的PAEKS方案。基于DDH假设，证明了该方案满足多密文和多活板门的安全标准。此外，在搜索阶段采用并行搜索方法，以提高搜索过程的整体效率。实验结果表明，与其他双线性配对算法相比，该算法的计算时间缩短了7 ~ 28倍，具有更高的搜索效率，更适合于实际应用。

{"title":"Efficient public key authenticated searchable encryption scheme without bilinear pairings","authors":"Meijuan Huang , Jingjie Gan , Bo Yang , Hongzhen Du , Yanqi Zhao","doi":"10.1016/j.csi.2025.104016","DOIUrl":"10.1016/j.csi.2025.104016","url":null,"abstract":"<div><div>The issue of searching for data within ciphertext files in cloud storage is effectively resolved through public key encryption with keyword search (PEKS). The main security problem it has is the internal keyword guessing attack (IKGA), for which Huang et al. proposed a novel scheme, public key authenticated encryption with keyword search (PAEKS), which employs a combination of encryption and authentication to enhance the security of the scheme. Most PAEKS algorithms utilize bilinear pairings, which are inherently costly from a computational perspective and also offer only single-keyword ciphertext security guarantees. In light of the aforementioned considerations, this paper presents a PAEKS scheme that does not employ bilinear pairings. The scheme is demonstrated to satisfy the criteria of multi-ciphertext and multi-trapdoor security, based on the DDH assumption. Furthermore, the parallel search method is employed during the search phase with the objective of enhancing the overall efficiency of the search process. Ultimately, the experimental results demonstrate that the computational time of the proposed scheme is reduced by a factor of 7 to 28 compared to other schemes using bilinear pairings, and our scheme has higher search efficiency and is more suitable for practical applications.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"94 ","pages":"Article 104016"},"PeriodicalIF":4.1,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922938","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 hybrid coot based CNN model for thyroid cancer detection 一种基于杂交白骨的甲状腺癌检测CNN模型

IF 4.1 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Standards & Interfaces

Pub Date : 2025-05-04 DOI: 10.1016/j.csi.2025.104018

Zeynep İlkiliç Aytaç , İsmail İşeri , Beşir Dandil

Thyroid cancer is one of the most common endocrine malignancies, and early diagnosis is crucial for effective treatment. Fine-needle aspiration biopsy (FNAB) is widely used for diagnosis, but its accuracy depends on expert interpretation, which can be subjective. Recent advances in deep learning, particularly Convolutional Neural Networks (CNNs), have shown promise in automating and improving diagnostic accuracy from biopsy images. However, optimizing CNN architectures remains a challenge, as selecting the best layer parameters significantly impacts performance. Traditional approaches for selecting optimal CNN parameters often depend on exhaustive trial-and-error methods, which are computationally expensive and do not always yield globally optimal solutions. This process is both time-consuming and does not guarantee the precise attainment of an optimal CNN model. In this study, a novel approach is introduced to optimize CNN parameters by utilizing the COOT Metaheuristic Optimization Algorithm, proposing a new model named COOT-CNN for thyroid cancer detection. The COOT algorithm, formulated in 2021 and inspired by the behavioral optimization of waterfowl, is employed in this research to determine the optimal layers and parameters of the CNN model for thyroid cancer diagnosis. This method facilitates efficient optimization of layer parameters through a well-designed coding scheme. The model’s efficacy is assessed using thyroid fine needle aspiration biopsy data, categorized into two classes. Performance of the proposed approach is evaluated by comparing it with traditional CNN, Particle Swarm Optimization-based CNN model (PSOCNN), and Gray Wolf Optimization-based CNN model (GWOCNN). The proposed model was found to achieve higher accuracy compared to conventional CNN, PSOCNN, and GWOCNN models.

甲状腺癌是最常见的内分泌恶性肿瘤之一，早期诊断对有效治疗至关重要。细针穿刺活检（FNAB）广泛用于诊断，但其准确性取决于专家的解释，这可能是主观的。深度学习的最新进展，特别是卷积神经网络（cnn），在自动化和提高活检图像诊断准确性方面显示出了希望。然而，优化CNN架构仍然是一个挑战，因为选择最佳的层参数会显著影响性能。选择最优CNN参数的传统方法通常依赖于穷举试错法，这种方法计算成本高，并且并不总是产生全局最优解。这个过程既耗时又不能保证精确地获得最优的CNN模型。本研究引入了一种利用COOT元启发式优化算法优化CNN参数的新方法，提出了一种新的甲状腺癌检测模型COOT-CNN。本研究采用受水禽行为优化启发，于2021年提出的COOT算法，确定甲状腺癌诊断CNN模型的最优层数和参数。该方法通过精心设计的编码方案，实现了层参数的高效优化。该模型的疗效评估使用甲状腺细针穿刺活检数据，分为两类。通过与传统CNN、基于粒子群优化的CNN模型（PSOCNN）和基于灰狼优化的CNN模型（GWOCNN）进行比较，评价了该方法的性能。与传统的CNN、PSOCNN和GWOCNN模型相比，该模型具有更高的精度。

{"title":"A hybrid coot based CNN model for thyroid cancer detection","authors":"Zeynep İlkiliç Aytaç , İsmail İşeri , Beşir Dandil","doi":"10.1016/j.csi.2025.104018","DOIUrl":"10.1016/j.csi.2025.104018","url":null,"abstract":"<div><div>Thyroid cancer is one of the most common endocrine malignancies, and early diagnosis is crucial for effective treatment. Fine-needle aspiration biopsy (FNAB) is widely used for diagnosis, but its accuracy depends on expert interpretation, which can be subjective. Recent advances in deep learning, particularly Convolutional Neural Networks (CNNs), have shown promise in automating and improving diagnostic accuracy from biopsy images. However, optimizing CNN architectures remains a challenge, as selecting the best layer parameters significantly impacts performance. Traditional approaches for selecting optimal CNN parameters often depend on exhaustive trial-and-error methods, which are computationally expensive and do not always yield globally optimal solutions. This process is both time-consuming and does not guarantee the precise attainment of an optimal CNN model. In this study, a novel approach is introduced to optimize CNN parameters by utilizing the COOT Metaheuristic Optimization Algorithm, proposing a new model named COOT-CNN for thyroid cancer detection. The COOT algorithm, formulated in 2021 and inspired by the behavioral optimization of waterfowl, is employed in this research to determine the optimal layers and parameters of the CNN model for thyroid cancer diagnosis. This method facilitates efficient optimization of layer parameters through a well-designed coding scheme. The model’s efficacy is assessed using thyroid fine needle aspiration biopsy data, categorized into two classes. Performance of the proposed approach is evaluated by comparing it with traditional CNN, Particle Swarm Optimization-based CNN model (PSO<img>CNN), and Gray Wolf Optimization-based CNN model (GWO<img>CNN). The proposed model was found to achieve higher accuracy compared to conventional CNN, PSO<img>CNN, and GWO<img>CNN models.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"94 ","pages":"Article 104018"},"PeriodicalIF":4.1,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922937","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