Computer Standards & Interfaces最新文献

Fuzzy-based security requirements quality assessing: Comparison of security experts and generative AI 基于模糊的安全需求质量评估：安全专家与生成式人工智能的比较

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

Computer Standards & Interfaces

Pub Date : 2026-01-28 DOI: 10.1016/j.csi.2026.104137

Asta Slotkienė, Jolanta Miliauskaitė, Rasa Karbauskaitė

Software systems that store and process large volumes of data are prime targets for increasingly sophisticated cyberattacks. Software engineers recognise that developing software completely free of defects or vulnerabilities is practically impossible, which makes security a critical quality characteristic of software products that must be addressed from the earliest stages of requirements engineering to avoid data loss, software failure, and ensure effective maintenance. Today, secure software engineering promotes proactive risk analysis, systematically identifying potential threats and integrating appropriate countermeasures into the requirements and development process. This paper presents an empirical investigation of security requirements engineering methodologies that integrate the experience of security experts and generative AI capabilities into the security requirements engineering (SRE) process. The empirical investigation results show that SRE based on Generative Artificial Intelligence (GenAI) capabilities still does not achieve the security expert's experience in specifying security requirements, while ensuring the quality of requirement specification based on security risks. We hope that our results will inspire researchers and practitioners to further explore the improvement of security requirements specifications using generative AI and fuzzy logic for SRE.

存储和处理大量数据的软件系统是日益复杂的网络攻击的主要目标。软件工程师认识到，开发完全没有缺陷或漏洞的软件实际上是不可能的，这使得安全性成为软件产品的一个关键质量特征，必须从需求工程的早期阶段开始解决，以避免数据丢失、软件故障，并确保有效的维护。今天，安全软件工程促进了前瞻性的风险分析，系统地识别潜在的威胁，并将适当的对策集成到需求和开发过程中。本文提出了安全需求工程方法的实证研究，该方法将安全专家的经验和生成人工智能能力集成到安全需求工程（SRE）过程中。实证调查结果表明，基于生成式人工智能（GenAI）能力的SRE在保证基于安全风险的需求规范质量的同时，仍不能达到安全专家在指定安全需求方面的经验。我们希望我们的研究结果能够激励研究人员和实践者进一步探索使用生成式人工智能和模糊逻辑来改进SRE的安全需求规范。

{"title":"Fuzzy-based security requirements quality assessing: Comparison of security experts and generative AI","authors":"Asta Slotkienė, Jolanta Miliauskaitė, Rasa Karbauskaitė","doi":"10.1016/j.csi.2026.104137","DOIUrl":"10.1016/j.csi.2026.104137","url":null,"abstract":"<div><div>Software systems that store and process large volumes of data are prime targets for increasingly sophisticated cyberattacks. Software engineers recognise that developing software completely free of defects or vulnerabilities is practically impossible, which makes security a critical quality characteristic of software products that must be addressed from the earliest stages of requirements engineering to avoid data loss, software failure, and ensure effective maintenance. Today, secure software engineering promotes proactive risk analysis, systematically identifying potential threats and integrating appropriate countermeasures into the requirements and development process. This paper presents an empirical investigation of security requirements engineering methodologies that integrate the experience of security experts and generative AI capabilities into the security requirements engineering (SRE) process. The empirical investigation results show that SRE based on Generative Artificial Intelligence (GenAI) capabilities still does not achieve the security expert's experience in specifying security requirements, while ensuring the quality of requirement specification based on security risks. We hope that our results will inspire researchers and practitioners to further explore the improvement of security requirements specifications using generative AI and fuzzy logic for SRE.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104137"},"PeriodicalIF":3.1,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077329","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

Research on optimizing network intrusion detection using deep learning and big data in intelligent elderly care 基于深度学习和大数据的智能养老网络入侵检测优化研究

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

Computer Standards & Interfaces

Pub Date : 2026-01-24 DOI: 10.1016/j.csi.2026.104136

Dai Huiying

Internet of Things devices are increasingly embedded in elderly care services, expanding exposure to network intrusions that can disrupt remote monitoring and compromise sensitive data. This study develops a stacked deep-learning intrusion detection meta-model for elderly care network settings and evaluates it using the Network Security Laboratory–Knowledge Discovery and Data Mining (NSL-KDD) and Canadian Institute for Cybersecurity Intrusion Detection System 2018 (CICIDS2018) datasets. The approach integrates deep neural networks, convolutional neural networks, recurrent neural networks with long short-term memory and gated recurrent units, and autoencoders by fusing their calibrated decision outputs in a second-stage learner. Data preprocessing included encoding of categorical attributes, normalization, and class-imbalance handling, with model comparison performed using five-fold cross-validation and one-way analysis of variance with Tukey’s post hoc contrasts. The proposed meta-model achieved 99.85% accuracy, 99.2% precision, 99.1% recall, and a 99.15% F1 score, exceeding individual base learners and comparator ensembles, and showed strong detection for frequent service-disruption and reconnaissance attacks while remaining less sensitive to rare exploit categories (approximately 0.85 precision/recall for low-support classes). These results indicate that decision-level fusion can improve robustness under class imbalance and supports low-latency deployment in resource-constrained care facilities when implemented in an edge–cloud monitoring workflow.

物联网设备越来越多地嵌入到老年护理服务中，这增加了网络入侵的风险，可能会破坏远程监控并泄露敏感数据。本研究开发了一种用于老年护理网络设置的堆叠深度学习入侵检测元模型，并使用网络安全实验室-知识发现和数据挖掘（NSL-KDD）和加拿大网络安全入侵检测系统研究所2018 （CICIDS2018）数据集对其进行评估。该方法集成了深度神经网络、卷积神经网络、具有长短期记忆和门控循环单元的循环神经网络，以及通过在第二阶段学习器中融合其校准决策输出的自编码器。数据预处理包括分类属性编码、归一化和类别不平衡处理，模型比较使用五倍交叉验证和Tukey事后对比的单向方差分析。所提出的元模型达到了99.85%的准确率、99.2%的精度、99.1%的召回率和99.15%的F1分数，超过了单个基础学习器和比较器集合，并且对频繁的服务中断和侦察攻击表现出很强的检测能力，同时对罕见的漏洞类别保持较低的敏感性（低支持类的精度/召回率约为0.85）。这些结果表明，决策级融合可以提高类不平衡下的鲁棒性，并支持在资源受限的医疗机构中实现低延迟部署。

{"title":"Research on optimizing network intrusion detection using deep learning and big data in intelligent elderly care","authors":"Dai Huiying","doi":"10.1016/j.csi.2026.104136","DOIUrl":"10.1016/j.csi.2026.104136","url":null,"abstract":"<div><div>Internet of Things devices are increasingly embedded in elderly care services, expanding exposure to network intrusions that can disrupt remote monitoring and compromise sensitive data. This study develops a stacked deep-learning intrusion detection meta-model for elderly care network settings and evaluates it using the Network Security Laboratory–Knowledge Discovery and Data Mining (NSL-KDD) and Canadian Institute for Cybersecurity Intrusion Detection System 2018 (CICIDS2018) datasets. The approach integrates deep neural networks, convolutional neural networks, recurrent neural networks with long short-term memory and gated recurrent units, and autoencoders by fusing their calibrated decision outputs in a second-stage learner. Data preprocessing included encoding of categorical attributes, normalization, and class-imbalance handling, with model comparison performed using five-fold cross-validation and one-way analysis of variance with Tukey’s post hoc contrasts. The proposed meta-model achieved 99.85% accuracy, 99.2% precision, 99.1% recall, and a 99.15% F1 score, exceeding individual base learners and comparator ensembles, and showed strong detection for frequent service-disruption and reconnaissance attacks while remaining less sensitive to rare exploit categories (approximately 0.85 precision/recall for low-support classes). These results indicate that decision-level fusion can improve robustness under class imbalance and supports low-latency deployment in resource-constrained care facilities when implemented in an edge–cloud monitoring workflow.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104136"},"PeriodicalIF":3.1,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077331","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

Highway to Hack — Security gaps in ETSI ITS standards 高速公路黑客-安全漏洞在ETSI ITS标准

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

Computer Standards & Interfaces

Pub Date : 2026-01-21 DOI: 10.1016/j.csi.2026.104133

Roberto Gesteira-Miñarro , Takahito Yoshizawa , Rafael Palacios , Gregorio López

Vehicle-to-Everything (V2X) communication technologies are revolutionizing transportation by enabling real-time information exchange among vehicles, infrastructure, pedestrians, and networks. While these technologies offer significant benefits in terms of road safety, traffic efficiency, and support for autonomous driving, they also introduce critical security and privacy risks due to their decentralized and dynamic nature. In this paper, we perform an analysis of the ETSI Intelligent Transport System (ITS) standards, specifications and reports to identify vulnerabilities that could be exploited to cause cyber–physical damages. We focus particularly on Cooperative Awareness Messages (CAM) and Decentralized Environmental Notification Messages (DENM) in the ETSI ITS standard, and pseudonym ID mechanisms. We identified several security issues, including vulnerabilities that lead to replay attacks, identity-based attacks such as spoofing and Sybil attacks, as well as grayhole attacks. We present attack scenarios where the issues found can be leveraged to compromise road safety, and quantify their potential impact through simulations using Eclipse SUMO. These scenarios might be relevant during a transition period where V2X-enabled vehicles coexist with legacy vehicles. Furthermore, we propose mitigations to address the identified issues. Our findings highlight the need for stronger security measures in V2X systems to ensure both safety and security in future intelligent transportation systems.

车辆到一切（V2X）通信技术通过实现车辆、基础设施、行人和网络之间的实时信息交换，正在彻底改变交通运输。虽然这些技术在道路安全、交通效率和对自动驾驶的支持方面提供了显著的好处，但由于它们的分散性和动态性，它们也带来了关键的安全和隐私风险。在本文中，我们对ETSI智能交通系统（ITS）标准、规范和报告进行了分析，以确定可能被利用来造成网络物理损害的漏洞。我们特别关注ETSI ITS标准中的协作意识消息（CAM）和分散环境通知消息（DENM），以及假名ID机制。我们发现了几个安全问题，包括导致重放攻击、基于身份的攻击（如欺骗和Sybil攻击）以及灰洞攻击的漏洞。我们给出了攻击场景，其中发现的问题可以被用来危害道路安全，并通过使用Eclipse SUMO进行模拟来量化它们的潜在影响。在支持v2x的车辆与传统车辆共存的过渡时期，这些场景可能是相关的。此外，我们提出了缓解措施，以解决已确定的问题。我们的研究结果强调了在V2X系统中需要更强大的安全措施，以确保未来智能交通系统的安全性。

{"title":"Highway to Hack — Security gaps in ETSI ITS standards","authors":"Roberto Gesteira-Miñarro , Takahito Yoshizawa , Rafael Palacios , Gregorio López","doi":"10.1016/j.csi.2026.104133","DOIUrl":"10.1016/j.csi.2026.104133","url":null,"abstract":"<div><div>Vehicle-to-Everything (V2X) communication technologies are revolutionizing transportation by enabling real-time information exchange among vehicles, infrastructure, pedestrians, and networks. While these technologies offer significant benefits in terms of road safety, traffic efficiency, and support for autonomous driving, they also introduce critical security and privacy risks due to their decentralized and dynamic nature. In this paper, we perform an analysis of the ETSI Intelligent Transport System (ITS) standards, specifications and reports to identify vulnerabilities that could be exploited to cause cyber–physical damages. We focus particularly on Cooperative Awareness Messages (CAM) and Decentralized Environmental Notification Messages (DENM) in the ETSI ITS standard, and pseudonym ID mechanisms. We identified several security issues, including vulnerabilities that lead to replay attacks, identity-based attacks such as spoofing and Sybil attacks, as well as grayhole attacks. We present attack scenarios where the issues found can be leveraged to compromise road safety, and quantify their potential impact through simulations using Eclipse SUMO. These scenarios might be relevant during a transition period where V2X-enabled vehicles coexist with legacy vehicles. Furthermore, we propose mitigations to address the identified issues. Our findings highlight the need for stronger security measures in V2X systems to ensure both safety and security in future intelligent transportation systems.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104133"},"PeriodicalIF":3.1,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037247","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 secure reversible image hiding approach combining block based intelligence with dual stego matrix encoding 一种基于分块智能和双隐进矩阵编码相结合的安全可逆图像隐藏方法

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

Computer Standards & Interfaces

Pub Date : 2026-01-19 DOI: 10.1016/j.csi.2026.104131

Minakshi Sarkar , Kankana Datta , Bidesh Chakraborty , Indrajit Banerjee

With the rapid growth of communication technologies, securing private data during transmission over public networks has become a significant challenge. Traditional data hiding methods, such as modifying the least significant bits (LSBs) of image pixels, often lead to visible distortion, especially when embedding large amounts of data. To address this issue, we propose a novel image steganography method that combines AES encryption, a Fine Tuning Transformer (FTT) classifier, and LSB embedding integrated with a Binary Lower Triangular Matrix (BLTM) for secure data hiding. In the proposed approach, the secret image is first encrypted using AES to ensure data confidentiality. The FTT classifier then predicts three block labels that determine the amount of data to be embedded in each block. Using the BLTM concept along with LSB substitution, the encrypted data is embedded into both cover images. Finally, to further enhance security, the two stego images are encrypted using a master key. Experimental results show that the proposed scheme provides high imperceptibility. Even at the maximum embedding rate of 0.93 bpp, the PSNR values remain above 56 dB, while the Mean Square Error (MSE) is low and the Structural Similarity Index (SSIM) stays above 0.97. The proposed dual-image steganographic framework advances secure multimedia communication by supporting image authentication, tamper detection, and forgery prevention benefiting domains such as healthcare, defense, and digital rights protection. It also offers adaptive payload allocation and strong robustness against noise, salt-and-pepper, opaque masking, and grid occlusion attacks, making the system both reliable and attack resilient.

随着通信技术的快速发展，在公共网络上传输私有数据的安全性已成为一个重大挑战。传统的数据隐藏方法，如修改图像像素的最低有效位（LSBs），通常会导致可见的失真，特别是在嵌入大量数据时。为了解决这个问题，我们提出了一种新的图像隐写方法，该方法结合了AES加密、微调变压器（FTT）分类器和集成了二进制下三角矩阵（BLTM）的LSB嵌入，以实现安全的数据隐藏。在该方法中，首先使用AES对秘密图像进行加密，以确保数据的机密性。然后，FTT分类器预测三个块标签，这些块标签确定要嵌入每个块中的数据量。使用BLTM概念和LSB替换，加密的数据被嵌入到两个封面图像中。最后，为了进一步提高安全性，使用主密钥对两个隐写图像进行加密。实验结果表明，该方案具有较高的隐蔽性。即使在最大嵌入率为0.93 bpp时，PSNR值仍保持在56 dB以上，均方误差（MSE）较低，结构相似指数（SSIM）保持在0.97以上。提出的双图像隐写框架通过支持图像认证、篡改检测和伪造预防，提高了安全的多媒体通信，有利于医疗保健、国防和数字版权保护等领域。它还提供自适应有效载荷分配和强大的抗噪声、盐和胡椒、不透明掩蔽和网格遮挡攻击的鲁棒性，使系统既可靠又具有抗攻击能力。

{"title":"A secure reversible image hiding approach combining block based intelligence with dual stego matrix encoding","authors":"Minakshi Sarkar , Kankana Datta , Bidesh Chakraborty , Indrajit Banerjee","doi":"10.1016/j.csi.2026.104131","DOIUrl":"10.1016/j.csi.2026.104131","url":null,"abstract":"<div><div>With the rapid growth of communication technologies, securing private data during transmission over public networks has become a significant challenge. Traditional data hiding methods, such as modifying the least significant bits (LSBs) of image pixels, often lead to visible distortion, especially when embedding large amounts of data. To address this issue, we propose a novel image steganography method that combines AES encryption, a Fine Tuning Transformer (FTT) classifier, and LSB embedding integrated with a Binary Lower Triangular Matrix (BLTM) for secure data hiding. In the proposed approach, the secret image is first encrypted using AES to ensure data confidentiality. The FTT classifier then predicts three block labels that determine the amount of data to be embedded in each block. Using the BLTM concept along with LSB substitution, the encrypted data is embedded into both cover images. Finally, to further enhance security, the two stego images are encrypted using a master key. Experimental results show that the proposed scheme provides high imperceptibility. Even at the maximum embedding rate of 0.93 bpp, the PSNR values remain above 56 dB, while the Mean Square Error (MSE) is low and the Structural Similarity Index (SSIM) stays above 0.97. The proposed dual-image steganographic framework advances secure multimedia communication by supporting image authentication, tamper detection, and forgery prevention benefiting domains such as healthcare, defense, and digital rights protection. It also offers adaptive payload allocation and strong robustness against noise, salt-and-pepper, opaque masking, and grid occlusion attacks, making the system both reliable and attack resilient.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104131"},"PeriodicalIF":3.1,"publicationDate":"2026-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037168","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

Publicly verifiable covert two-party computation with punitive blame 带有惩罚性责备的可公开验证的隐蔽两方计算

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

Computer Standards & Interfaces

Pub Date : 2026-01-17 DOI: 10.1016/j.csi.2026.104132

Chuan Zhao , Jun Xu , Shengnan Zhao , Song Han , Chunpeng Ge , Qiuliang Xu

Publicly verifiable covert (PVC) security model allows honest parties in secure multi-party computation (MPC) to generate a public proof that can be verified by an external party to check misbehavior. PVC first takes into account the deterrent effects of publicly damaging the reputation of dishonest parties. However, the dishonest party may still choose to cheat if the potential gains outweigh the minor reputational consequences. Moreover, using proxies like shell companies can insulate the actual party from direct reputational harm in case of detected cheating. Therefore, a more realistic deterrent in PVC is required to improve its practicality. Inspired by the financial restriction mechanism (Faust et al. PKC 2022), we propose a PVC security model incorporating punitive blame to enhance the deterrent effects of the dishonest party. Our security model achieves strong defamation resistance by allowing participants to carry out a series of algorithms, including Blame, PreJudge, Appeal, and Judge. Furthermore, based on a new compatible extension technique for Signed-OT, we propose a secure two-party protocol in the new PVC model. The experiment shows approximate improvements in computational and communication costs of

1.5 - 2.6 \times

and

2.3 - 2.9 \times

over the PVC protocol, respectively.

公开可验证的隐蔽（PVC）安全模型允许安全多方计算（MPC）中的诚实各方生成可由外部方验证以检查不当行为的公开证明。PVC首先考虑到公开损害不诚实当事人声誉的威慑作用。然而，如果潜在的收益超过了轻微的声誉后果，不诚实的一方仍然可能选择欺骗。此外，使用像空壳公司这样的代理可以使实际的一方在被发现作弊的情况下免受直接的声誉损害。因此，在PVC中需要更现实的威慑，以提高其实用性。受金融约束机制的启发（Faust等）。PKC 2022)，我们提出了一个包含惩罚性责任的PVC安全模型，以增强对不诚实一方的威慑作用。我们的安全模型通过允许参与者执行一系列算法，包括Blame、PreJudge、Appeal和Judge，实现了强大的抗诽谤能力。在此基础上，基于一种新的可兼容的Signed-OT扩展技术，在新的PVC模型中提出了一种安全的双方协议。实验表明，与PVC协议相比，计算和通信成本分别提高了1.5 ~ 2.6倍和2.3 ~ 2.9倍。

{"title":"Publicly verifiable covert two-party computation with punitive blame","authors":"Chuan Zhao , Jun Xu , Shengnan Zhao , Song Han , Chunpeng Ge , Qiuliang Xu","doi":"10.1016/j.csi.2026.104132","DOIUrl":"10.1016/j.csi.2026.104132","url":null,"abstract":"<div><div>Publicly verifiable covert (PVC) security model allows honest parties in secure multi-party computation (MPC) to generate a public proof that can be verified by an external party to check misbehavior. PVC first takes into account the deterrent effects of publicly damaging the reputation of dishonest parties. However, the dishonest party may still choose to cheat if the potential gains outweigh the minor reputational consequences. Moreover, using proxies like shell companies can insulate the actual party from direct reputational harm in case of detected cheating. Therefore, a more realistic deterrent in PVC is required to improve its practicality. Inspired by the financial restriction mechanism (Faust et al. PKC 2022), we propose a PVC security model incorporating punitive blame to enhance the deterrent effects of the dishonest party. Our security model achieves strong defamation resistance by allowing participants to carry out a series of algorithms, including Blame, PreJudge, Appeal, and Judge. Furthermore, based on a new compatible extension technique for Signed-OT, we propose a secure two-party protocol in the new PVC model. The experiment shows approximate improvements in computational and communication costs of <span><math><mrow><mn>1</mn><mo>.</mo><mn>5</mn><mo>−</mo><mn>2</mn><mo>.</mo><mn>6</mn><mo>×</mo></mrow></math></span> and <span><math><mrow><mn>2</mn><mo>.</mo><mn>3</mn><mo>−</mo><mn>2</mn><mo>.</mo><mn>9</mn><mo>×</mo></mrow></math></span> over the PVC protocol, respectively.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104132"},"PeriodicalIF":3.1,"publicationDate":"2026-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037169","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

Privacy-preserving kNN classification for cross-platform electric vehicle data analytics 跨平台电动汽车数据分析的隐私保护kNN分类

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

Computer Standards & Interfaces

Pub Date : 2026-01-16 DOI: 10.1016/j.csi.2026.104134

Zhicheng Li , Jian Xu , Nan Zhang , Teng Lu , Peijun Li , Nian Wang , Qiuyue Wang

Cloud and edge platforms increasingly host machine learning workloads, yet outsourcing

k

-Nearest Neighbors (

k

NN) raises acute risks to data privacy and computation integrity. Existing perturbation and partially homomorphic approaches either leak information or fail to scale, while conventional FHE comparisons and interactive MPC protocols impose heavy costs. We propose two complementary schemes for privacy-preserving

k

NN tailored to cross-platform EV analytics. First, a single-server FHE design performs encrypted inner products and exact squared Euclidean distances using matrix-optimized packing to parallelize feature-wise operations and batch queries, reducing ciphertext count and multiplicative depth. Second, a two-server MPC design executes distance evaluation, fixed-network Top-

k

, and majority voting entirely on additive shares, with re-sharing to refresh randomness and hide access patterns. We formalize semi-honest threat models and prove input privacy and correctness. Additive-share MPC demonstrates plaintext-level accuracy, with FHE achieving non-interactive cloud processing and MPC delivering near real-time online latency at practical communication cost. The combined results show that strong privacy and practical efficiency for

k

NN can be achieved without exposing training data, queries, or intermediate computations.

云和边缘平台越来越多地托管机器学习工作负载，但外包k-近邻（kNN）会给数据隐私和计算完整性带来严重风险。现有的微扰和部分同态方法要么泄露信息，要么无法扩展，而传统的FHE比较和交互式MPC协议则带来了高昂的成本。我们提出了两种针对跨平台EV分析的隐私保护kNN互补方案。首先，单服务器FHE设计使用矩阵优化封装执行加密的内积和精确平方欧几里得距离，以并行化特征操作和批处理查询，减少密文计数和乘法深度。其次，双服务器MPC设计完全在附加共享上执行距离评估、固定网络Top-k和多数投票，并通过重新共享来刷新随机性和隐藏访问模式。我们形式化了半诚实的威胁模型，并证明了输入的隐私性和正确性。加法共享MPC展示了纯文本级别的准确性，FHE实现了非交互式云处理，MPC在实际通信成本下提供了接近实时的在线延迟。综合结果表明，在不暴露训练数据、查询或中间计算的情况下，可以实现kNN的强隐私性和实用效率。

{"title":"Privacy-preserving kNN classification for cross-platform electric vehicle data analytics","authors":"Zhicheng Li , Jian Xu , Nan Zhang , Teng Lu , Peijun Li , Nian Wang , Qiuyue Wang","doi":"10.1016/j.csi.2026.104134","DOIUrl":"10.1016/j.csi.2026.104134","url":null,"abstract":"<div><div>Cloud and edge platforms increasingly host machine learning workloads, yet outsourcing <span><math><mi>k</mi></math></span>-Nearest Neighbors (<span><math><mi>k</mi></math></span>NN) raises acute risks to data privacy and computation integrity. Existing perturbation and partially homomorphic approaches either leak information or fail to scale, while conventional FHE comparisons and interactive MPC protocols impose heavy costs. We propose two complementary schemes for privacy-preserving <span><math><mi>k</mi></math></span>NN tailored to cross-platform EV analytics. First, a single-server FHE design performs encrypted inner products and exact squared Euclidean distances using matrix-optimized packing to parallelize feature-wise operations and batch queries, reducing ciphertext count and multiplicative depth. Second, a two-server MPC design executes distance evaluation, fixed-network Top-<span><math><mi>k</mi></math></span>, and majority voting entirely on additive shares, with re-sharing to refresh randomness and hide access patterns. We formalize semi-honest threat models and prove input privacy and correctness. Additive-share MPC demonstrates plaintext-level accuracy, with FHE achieving non-interactive cloud processing and MPC delivering near real-time online latency at practical communication cost. The combined results show that strong privacy and practical efficiency for <span><math><mi>k</mi></math></span>NN can be achieved without exposing training data, queries, or intermediate computations.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104134"},"PeriodicalIF":3.1,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077245","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 Dynamic Multimodal Causal Graph framework for standardized Emotion Recognition in Conversations 对话中标准化情绪识别的动态多模态因果图框架

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

Computer Standards & Interfaces

Pub Date : 2026-01-16 DOI: 10.1016/j.csi.2026.104130

Ronghao Pan, José Antonio García-Díaz, Rafael Valencia-García

Understanding emotions in conversations is a fundamental challenge in affective computing. Emotional expressions evolve dynamically across dialogue turns and depend on multimodal cues such as speech, text, and facial behavior. However, existing multimodal models often rely on global attention mechanisms that overlook causal constraints. This allows information leakage from future turns and neglect of the speaker’s emotional evolution. To address these limitations, we propose the Dynamic Multimodal Causal Graph Emotion System (DMCGES). DMCGES integrates a restricted dynamic causal graph to ensure temporal coherence, as well as a speaker-specific memory module to capture affective trajectories and enhance multimodal alignment and robustness. The framework aligns with the IEEE 7010-2020 standard, which emphasizes integrating human well-being as a fundamental design principle in autonomous and intelligent systems. Experiments on the IEMOCAP and MELD benchmark datasets demonstrate that DMCGES outperforms state-of-the-art approaches in terms of accuracy and F1 score. On the IEMOCAP dataset, DMCGES achieved an accuracy of 69.36% and an F1 score of 69.49%, representing relative improvements of 1.95% and 2.39%, respectively. On the MELD dataset, our model achieved an accuracy of 62.38% and an F1 score of 62.03%, improving upon SACCMA’s results by 0.1% in accuracy and 2.73% in F1 score.

理解对话中的情绪是情感计算的一个基本挑战。情感表达在对话回合中动态演变，并依赖于多模态线索，如语音、文本和面部行为。然而，现有的多模态模型往往依赖于忽视因果约束的全局注意机制。这使得信息从未来的转折中泄露出来，并且忽略了说话者的情绪演变。为了解决这些限制，我们提出了动态多模态因果图情感系统（DMCGES）。DMCGES集成了一个受限制的动态因果图，以确保时间一致性，以及一个特定于说话人的记忆模块，以捕捉情感轨迹，增强多模态对齐和鲁棒性。该框架与IEEE 7010-2020标准保持一致，该标准强调将人类福祉作为自主和智能系统的基本设计原则。在IEMOCAP和MELD基准数据集上的实验表明，DMCGES在准确性和F1分数方面优于最先进的方法。在IEMOCAP数据集上，DMCGES的准确率为69.36%，F1得分为69.49%，分别相对提高了1.95%和2.39%。在MELD数据集上，我们的模型实现了62.38%的准确率和62.03%的F1分数，比sacma的结果提高了0.1%的准确率和2.73%的F1分数。

{"title":"A Dynamic Multimodal Causal Graph framework for standardized Emotion Recognition in Conversations","authors":"Ronghao Pan, José Antonio García-Díaz, Rafael Valencia-García","doi":"10.1016/j.csi.2026.104130","DOIUrl":"10.1016/j.csi.2026.104130","url":null,"abstract":"<div><div>Understanding emotions in conversations is a fundamental challenge in affective computing. Emotional expressions evolve dynamically across dialogue turns and depend on multimodal cues such as speech, text, and facial behavior. However, existing multimodal models often rely on global attention mechanisms that overlook causal constraints. This allows information leakage from future turns and neglect of the speaker’s emotional evolution. To address these limitations, we propose the Dynamic Multimodal Causal Graph Emotion System (DMCGES). DMCGES integrates a restricted dynamic causal graph to ensure temporal coherence, as well as a speaker-specific memory module to capture affective trajectories and enhance multimodal alignment and robustness. The framework aligns with the IEEE 7010-2020 standard, which emphasizes integrating human well-being as a fundamental design principle in autonomous and intelligent systems. Experiments on the IEMOCAP and MELD benchmark datasets demonstrate that DMCGES outperforms state-of-the-art approaches in terms of accuracy and F1 score. On the IEMOCAP dataset, DMCGES achieved an accuracy of 69.36% and an F1 score of 69.49%, representing relative improvements of 1.95% and 2.39%, respectively. On the MELD dataset, our model achieved an accuracy of 62.38% and an F1 score of 62.03%, improving upon SACCMA’s results by 0.1% in accuracy and 2.73% in F1 score.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104130"},"PeriodicalIF":3.1,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037245","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

Decentralized multi-client boolean keyword search for encrypted cloud storage 分布式多客户端布尔关键字搜索加密云存储

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

Computer Standards & Interfaces

Pub Date : 2026-01-14 DOI: 10.1016/j.csi.2026.104127

Xiwen Wang , Junqing Gong , Kai Zhang , Haifeng Qian

In multi-client searchable symmetric encryption (MC-SSE), multiple clients have the capability to conduct keyword searches on encrypted data hosted in cloud, where the outsourced data is contributed by a data owner. Unfortunately, all known MC-SSE addressing key escrow problem required establishing a secure channel between data owner and user, and might suffer from significant key storage overhead. Therefore, we present an effective decentralized MC-SSE (DMC-SSE) system without the key escrow problem for secure cloud storage, eliminating the secure channel between data owner and data user. In DMC-SSE, each client independently picks its public/secret key, while a bulletin board of user public keys takes the place of the central authority. Technically, we introduce a semi-generic construction framework of DMC-SSE, building upon Cash et al.’s OXT structure (CRYPTO 2013), which roughly combines Kolonelos, Malavolta and Wee’s distributed broadcast encryption scheme (ASIACRYPT 2023) and additionally introduces a distributed keyed pseudorandom function module for securely aggregating each client’s secret key.

在多客户端可搜索对称加密（MC-SSE）中，多个客户端能够对托管在云中的加密数据进行关键字搜索，其中外包数据由数据所有者提供。不幸的是，所有已知的MC-SSE解决密钥托管问题都需要在数据所有者和用户之间建立一个安全通道，并且可能会遭受重大的密钥存储开销。因此，我们提出了一种有效的分散式MC-SSE （DMC-SSE）系统，该系统不存在安全云存储的密钥托管问题，消除了数据所有者和数据用户之间的安全通道。在DMC-SSE中，每个客户端独立地选择其公钥/密钥，而用户公钥公告板取代了中央权威。从技术上讲，我们在Cash等人的OXT结构（CRYPTO 2013）的基础上引入了DMC-SSE的半通用构造框架，该框架大致结合了Kolonelos， Malavolta和Wee的分布式广播加密方案（ASIACRYPT 2023），并引入了分布式密钥伪随机功能模块，用于安全地聚合每个客户端的密钥。

{"title":"Decentralized multi-client boolean keyword search for encrypted cloud storage","authors":"Xiwen Wang , Junqing Gong , Kai Zhang , Haifeng Qian","doi":"10.1016/j.csi.2026.104127","DOIUrl":"10.1016/j.csi.2026.104127","url":null,"abstract":"<div><div>In multi-client searchable symmetric encryption (MC-SSE), multiple clients have the capability to conduct keyword searches on encrypted data hosted in cloud, where the outsourced data is contributed by a data owner. Unfortunately, all known MC-SSE addressing key escrow problem required establishing a secure channel between data owner and user, and might suffer from significant key storage overhead. Therefore, we present an effective decentralized MC-SSE (DMC-SSE) system without the key escrow problem for secure cloud storage, eliminating the secure channel between data owner and data user. In DMC-SSE, each client independently picks its public/secret key, while a bulletin board of user public keys takes the place of the central authority. Technically, we introduce a semi-generic construction framework of DMC-SSE, building upon Cash et al.’s OXT structure (CRYPTO 2013), which roughly combines Kolonelos, Malavolta and Wee’s distributed broadcast encryption scheme (ASIACRYPT 2023) and additionally introduces a distributed keyed pseudorandom function module for securely aggregating each client’s secret key.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104127"},"PeriodicalIF":3.1,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977135","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

Optimal shard number determination algorithm based on security and performance in sharded blockchain 基于安全性和性能的区块链分片数确定算法

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

Computer Standards & Interfaces

Pub Date : 2026-01-12 DOI: 10.1016/j.csi.2026.104128

Shangping Wang, Haotong Cao, Ruoxin Yan

Sharding technique has significantly increased the transaction processing capacity and scalability in blockchain systems but compromise security, particularly with increased vulnerability to “1/3 attacks” as shard numbers rise. Clearly, more shards are not always better, how to determine the optimal number of shards is essential yet often overlooked in existing research. To address the aforementioned issues, we propose a broadly applicable algorithm for determining the optimal number of shards in sharded blockchain based on security and performance (SPSN). Firstly, this work proposes a novel optimization model for sharded blockchain by considering the impacts of sharding on system security and performance. The idea is to find an optimal shard number that balances system efficiency (time required to process transactions) and security (system failure probability), ensuring that the system failure probability within acceptable limits while maximizing efficiency. Secondly, we propose a widely applicable algorithm to determine the optimal number of shards, which can be executed independently before sharding operations to ascertain the shard count that maximizes performance while ensuring system security. Lastly, experiments are conducted under four different system settings to demonstrate the specific methods. The results show that the proposed algorithm can effectively calculate the optimal shard number for most systems, demonstrating broad applicability and effectiveness, helping achieve a high-security, high-performance sharded blockchain system.

分片技术极大地提高了区块链系统的事务处理能力和可伸缩性，但也损害了安全性，特别是随着分片数量的增加，“1/3攻击”的脆弱性增加。显然，更多的分片并不总是更好，如何确定最佳的分片数量是至关重要的，但在现有的研究中经常被忽视。为了解决上述问题，我们提出了一种广泛适用的算法，用于根据安全性和性能（SPSN）确定分片区块链中的最佳分片数量。首先，本文通过考虑分片对系统安全性和性能的影响，提出了一种新的区块链分片优化模型。其思想是找到一个平衡系统效率（处理事务所需的时间）和安全性（系统故障概率）的最优分片数，确保系统故障概率在可接受的范围内，同时最大化效率。其次，我们提出了一种广泛适用的算法来确定最优分片数，该算法可以在分片操作之前独立执行，以确定在保证系统安全的同时最大限度地提高性能的分片数。最后，在四种不同的系统设置下进行了实验，验证了具体方法。结果表明，该算法可以有效地计算出大多数系统的最优分片数，具有广泛的适用性和有效性，有助于实现高安全性、高性能的分片区块链系统。

{"title":"Optimal shard number determination algorithm based on security and performance in sharded blockchain","authors":"Shangping Wang, Haotong Cao, Ruoxin Yan","doi":"10.1016/j.csi.2026.104128","DOIUrl":"10.1016/j.csi.2026.104128","url":null,"abstract":"<div><div>Sharding technique has significantly increased the transaction processing capacity and scalability in blockchain systems but compromise security, particularly with increased vulnerability to “1/3 attacks” as shard numbers rise. Clearly, more shards are not always better, how to determine the optimal number of shards is essential yet often overlooked in existing research. To address the aforementioned issues, we propose a broadly applicable algorithm for determining the optimal number of shards in sharded blockchain based on security and performance (SPSN). Firstly, this work proposes a novel optimization model for sharded blockchain by considering the impacts of sharding on system security and performance. The idea is to find an optimal shard number that balances system efficiency (time required to process transactions) and security (system failure probability), ensuring that the system failure probability within acceptable limits while maximizing efficiency. Secondly, we propose a widely applicable algorithm to determine the optimal number of shards, which can be executed independently before sharding operations to ascertain the shard count that maximizes performance while ensuring system security. Lastly, experiments are conducted under four different system settings to demonstrate the specific methods. The results show that the proposed algorithm can effectively calculate the optimal shard number for most systems, demonstrating broad applicability and effectiveness, helping achieve a high-security, high-performance sharded blockchain system.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104128"},"PeriodicalIF":3.1,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077330","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

Securing hashed timelock cross-chain protocol with trusted middleman in blockchain networks 区块链网络中基于可信中间人的散列时间锁跨链协议安全保护

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

Computer Standards & Interfaces

Pub Date : 2026-01-09 DOI: 10.1016/j.csi.2026.104129

Wenhua Huang, Yuwei Deng, Jingyu Feng, Gang Han, Wenbo Zhang

Cross-chain interoperability has emerged as a pivotal factor in enabling seamless data interaction and value circulation across diverse blockchain networks. Nevertheless, current cross-chain technologies necessitate advancements to satisfy the escalating need for efficient bidirectional data exchange. Addressing this, our work focuses on refining cross-chain protocols, with a core emphasis on elevating transaction efficiency, reliability, and security. Our innovation centers around a strengthened hashed timelock cross-chain protocol grounded in trusted middlemen. To safeguard the security and confidentiality of middlemen engaged in cross-chain transactions, we introduce an ingenious anonymous identity authentication mechanism. This mechanism empowers middlemen to execute auxiliary cross-chain transactions while concealing their actual identities. Additionally, we propose a behavior-based assessment of middlemen, utilizing distinct indicators to gauge their trustworthiness in each cross-chain transaction. We introduce both current and historical trust values, providing insights into middlemen's real-time reliability and long-term stability. This approach effectively thwarts attempts by malicious middlemen to manipulate trust values, mitigating security vulnerabilities in cross-chain transactions. Furthermore, by clearing redundant blocks, we not only decrease storage consumption but also facilitate the storage of a substantial amount of identity data and trust data of middlemen. Rigorous security analysis demonstrates our scheme's alignment with foundational security requirements and resilience against common attacks. Furthermore, our simulation results underscore the potency of our trust evaluation scheme, substantiating its efficacy in ensuring middlemen credibility and detecting malicious actors.

跨链互操作性已经成为在不同bb0网络中实现无缝数据交互和价值循环的关键因素。然而，当前的跨链技术需要进步，以满足对高效双向数据交换不断增长的需求。为了解决这个问题，我们的工作重点是改进跨链协议，核心重点是提高交易效率、可靠性和安全性。我们的创新围绕着一个基于可信中间商的强化散列时间锁跨链协议。为了保障从事跨链交易的中间商的安全和机密性，我们引入了一种巧妙的匿名身份认证机制。这种机制使中间商能够执行辅助的跨链交易，同时隐藏其实际身份。此外，我们建议对中间商进行基于行为的评估，利用不同的指标来衡量他们在每个跨链交易中的可信度。我们介绍了当前和历史的信任值，为中间商的实时可靠性和长期稳定性提供了见解。这种方法有效地阻止了恶意中间商操纵信任值的企图，减轻了跨链交易中的安全漏洞。此外，通过清除冗余块，不仅可以减少存储消耗，还可以方便存储大量中间商的身份数据和信任数据。严格的安全分析证明了我们的方案符合基本的安全需求和抵御常见攻击的弹性。此外，我们的模拟结果强调了我们的信任评估方案的效力，证实了它在确保中间商可信度和检测恶意行为者方面的有效性。

{"title":"Securing hashed timelock cross-chain protocol with trusted middleman in blockchain networks","authors":"Wenhua Huang, Yuwei Deng, Jingyu Feng, Gang Han, Wenbo Zhang","doi":"10.1016/j.csi.2026.104129","DOIUrl":"10.1016/j.csi.2026.104129","url":null,"abstract":"<div><div>Cross-chain interoperability has emerged as a pivotal factor in enabling seamless data interaction and value circulation across diverse blockchain networks. Nevertheless, current cross-chain technologies necessitate advancements to satisfy the escalating need for efficient bidirectional data exchange. Addressing this, our work focuses on refining cross-chain protocols, with a core emphasis on elevating transaction efficiency, reliability, and security. Our innovation centers around a strengthened hashed timelock cross-chain protocol grounded in trusted middlemen. To safeguard the security and confidentiality of middlemen engaged in cross-chain transactions, we introduce an ingenious anonymous identity authentication mechanism. This mechanism empowers middlemen to execute auxiliary cross-chain transactions while concealing their actual identities. Additionally, we propose a behavior-based assessment of middlemen, utilizing distinct indicators to gauge their trustworthiness in each cross-chain transaction. We introduce both current and historical trust values, providing insights into middlemen's real-time reliability and long-term stability. This approach effectively thwarts attempts by malicious middlemen to manipulate trust values, mitigating security vulnerabilities in cross-chain transactions. Furthermore, by clearing redundant blocks, we not only decrease storage consumption but also facilitate the storage of a substantial amount of identity data and trust data of middlemen. Rigorous security analysis demonstrates our scheme's alignment with foundational security requirements and resilience against common attacks. Furthermore, our simulation results underscore the potency of our trust evaluation scheme, substantiating its efficacy in ensuring middlemen credibility and detecting malicious actors.</div></div>","PeriodicalId":50635,"journal":{"name":"Computer Standards & Interfaces","volume":"97 ","pages":"Article 104129"},"PeriodicalIF":3.1,"publicationDate":"2026-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977134","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