Journal of Network and Computer Applications最新文献

A MLOps architecture for near real-time distributed Stream Learning operation deployment

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-17 DOI: 10.1016/j.jnca.2025.104169

Miguel G. Rodrigues, Eduardo K. Viegas, Altair O. Santin, Fabricio Enembreck

{"title":"A MLOps architecture for near real-time distributed Stream Learning operation deployment","authors":"Miguel G. Rodrigues, Eduardo K. Viegas, Altair O. Santin, Fabricio Enembreck","doi":"10.1016/j.jnca.2025.104169","DOIUrl":"10.1016/j.jnca.2025.104169","url":null,"abstract":"<div><div>Traditional architectures for implementing Machine Learning Operations (MLOps) usually struggle to cope with the demands of Stream Learning (SL) environments, where deployed models must be incrementally updated at scale and in near real-time to handle a constantly evolving data stream. This paper proposes a new distributed architecture adapted for deploying and updating SL models under the MLOps framework, implemented twofold. First, we structure the core components as microservices deployed on a container orchestration environment, ensuring low computational overhead and high scalability. Second, we propose a periodic model versioning strategy that facilitates seamless updates of SL models without degrading system accuracy. By leveraging the inherent characteristics of SL algorithms, we trigger the model versioning task only when their decision boundaries undergo significant adjustments. This allows our architecture to support scalable inference while handling incremental SL updates, enabling high throughput and model accuracy in production settings. Experiments conducted on a proposal’s prototype implemented as a distributed microservice architecture on Kubernetes attested to our scheme’s feasibility. Our architecture can scale inference throughput as needed, delivering updated SL models in less than 2.5 s, supporting up to 8 inference endpoints while maintaining accuracy similar to traditional single-endpoint setups.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104169"},"PeriodicalIF":7.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642734","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

Comprehensive phishing detection: A multi-channel approach with variants TCN fusion leveraging URL and HTML features

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-17 DOI: 10.1016/j.jnca.2025.104170

Ali Aljofey , Saifullahi Aminu Bello , Jian Lu , Chen Xu

{"title":"Comprehensive phishing detection: A multi-channel approach with variants TCN fusion leveraging URL and HTML features","authors":"Ali Aljofey , Saifullahi Aminu Bello , Jian Lu , Chen Xu","doi":"10.1016/j.jnca.2025.104170","DOIUrl":"10.1016/j.jnca.2025.104170","url":null,"abstract":"<div><div>Phishing represents a major threat to the financial and privacy security of Internet users, and often serves as a precursor to cyberattacks. While many deep learning-based methods focus on analyzing URLs to detect phishing due to their simplicity and efficiency, they face challenges. Hidden phishing websites may employ tactics like concealing URL addresses, deceiving deep learning models, and attackers frequently change URLs, which presents obstacles to effective detection. In this study, we introduce a robust multi-channel temporal convolutional network (TCN) approach designed for precise phishing website detection, emphasizing the extraction of features from both URL and HTML components. Our hybrid methodology combines URL character embedding and various handcrafted features, using a two-channel input structure. These inputs undergo embedding and SpatialDropout1D before integration into diverse TCN layers, capturing features effectively. Outputs from TCN layers in both channels are concatenated, globally max-pooled, and late fused for binary webpage classification. Our approach demonstrates notable contributions, including novel features, meticulous architecture, and heightened accuracy. Experimentally, our approach achieves 99.81% accuracy on our dataset and 98.16% and 98.96% on two benchmark datasets, respectively. It outperforms state-of-the-art methods on real phishing webpages, demonstrating superior performance with reduced reliance on labeled data.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104170"},"PeriodicalIF":7.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654552","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

CBRFL: A framework for Committee-based Byzantine-Resilient Federated Learning

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-15 DOI: 10.1016/j.jnca.2025.104165

Gang Xu , Lele Lei , Yanhui Mao , Zongpeng Li , Xiu-Bo Chen , Kejia Zhang

{"title":"CBRFL: A framework for Committee-based Byzantine-Resilient Federated Learning","authors":"Gang Xu , Lele Lei , Yanhui Mao , Zongpeng Li , Xiu-Bo Chen , Kejia Zhang","doi":"10.1016/j.jnca.2025.104165","DOIUrl":"10.1016/j.jnca.2025.104165","url":null,"abstract":"<div><div>Federated Learning (FL), a decentralized machine learning paradigm, has gained attention for enabling collaborative model training without sharing raw data. However, traditional FL architectures rely on a central server, creating trust issues, single points of failure, and vulnerabilities to Byzantine attacks due to the lack of effective gradient validation. In this paper, we introduce the Committee-Based Byzantine-Resilient Federated Learning Framework (CBRFL), which decentralizes using a blockchain-based off-chain committee consensus mechanism for gradient validation and adaptive aggregation, eliminating the need for a central server. Furthermore, we present a momentum and adaptive global learning rate mechanism to improve training stability, along with a contribution and reputation system to enhance the reliability of committee members. The experimental results show that CBRFL outperforms robust FL algorithms across four federated heterogeneous datasets and three attack methods. Without attacks, CBRFL performs similarly to leading heterogeneous FL baselines in most scenarios.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104165"},"PeriodicalIF":7.7,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654551","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

Tensor-based ranking-hiding privacy-preserving scheme for cloud-fog-edge cooperative cyber–physical-social systems

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-13 DOI: 10.1016/j.jnca.2025.104167

Jing Yu , Yan Xiao , Lianhua Chi , Shunli Zhang , Zongmin Cui

{"title":"Tensor-based ranking-hiding privacy-preserving scheme for cloud-fog-edge cooperative cyber–physical-social systems","authors":"Jing Yu , Yan Xiao , Lianhua Chi , Shunli Zhang , Zongmin Cui","doi":"10.1016/j.jnca.2025.104167","DOIUrl":"10.1016/j.jnca.2025.104167","url":null,"abstract":"<div><div>Users living in Cyber-Physical-Social Systems (CPSS) generate massive amounts of data every day. The CPSS data may imply some reliable rules that can help CPSS better provide highly reliable services to humans. Nevertheless, the high-level reliable rules are very difficult to be mined and formalized. Therefore, we propose a Cloud-Fog-Edge Cooperative Reliable CPSS (CFECRC) framework for possibly adding reliable rules into CPSS. Ranked data is an important type of data in CPSS. How to design a secure, accurate and efficient ranking-hiding privacy-preserving scheme is a key challenge in CFECRC framework. However, existing privacy-preserving methods still have various shortcomings in the trade-off among privacy-preserving, analytic accuracy, and computational efficiency for ranking-hiding. To address the shortcomings, we propose a Tensor-based Ranking-Hiding Privacy-Preserving scheme (TRHPP) for CFECRC framework. First, we construct a set of 5th-order tensors to synthetically model item, user, location, time and weather as a whole to enhance analytic accuracy. Second, we obfuscate CPSS data and hide data ranking based on the obfuscated data to strengthen privacy-preserving and decrease computational overhead. The experimental results show that our scheme significantly outperforms existing classical schemes in privacy-preserving, analytic accuracy and computational efficiency simultaneously. This further verifies the feasibility of our framework.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104167"},"PeriodicalIF":7.7,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642735","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 comprehensive survey on channel hopping and scheduling enhancements for TSCH networks

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-08 DOI: 10.1016/j.jnca.2025.104164

Martina Balbi , Lance Doherty , Thomas Watteyne

引用次数: 0

ZBR: Zone-based routing in quantum networks with efficient entanglement distribution

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-08 DOI: 10.1016/j.jnca.2025.104156

Pankaj Kumar, Binayak Kar

{"title":"ZBR: Zone-based routing in quantum networks with efficient entanglement distribution","authors":"Pankaj Kumar, Binayak Kar","doi":"10.1016/j.jnca.2025.104156","DOIUrl":"10.1016/j.jnca.2025.104156","url":null,"abstract":"<div><div>The quantum network aims to establish connections among multiple quantum nodes, supporting various innovative applications. Many of these applications necessitate the sharing of entangled pairs among communicating parties. However, the inherent nature of entanglement leads to an exponential decrease as the distance between quantum nodes increases. This phenomenon makes it challenging for entangled pairs shared by quantum nodes to fulfill end-to-end entanglement routing requests, resulting in significant communication loss between these nodes. To tackle this challenge, we proposed Zone-Based Routing (ZBR) for quantum networks, which effectively handles end-to-end entanglement distribution. The core concept of zone-based routing involves creating zones containing source and destination pairs to facilitate effective entanglement distribution within each zone. We introduce Zone-Based Path Selection (ZBPS) and Zone-Based Entanglement Purification (ZBEP) algorithms to implement this approach. The main idea of the ZBPS algorithm is to select a routing path based on the flow capacity of adjacent links. Whereas, the ZBEP algorithm focuses on entanglement fidelity purification of the chosen path. These algorithms collectively maintain entanglement distribution, high fidelity, and throughput in quantum networks. Our simulation results demonstrate a significant improvement in entanglement distribution within quantum networks compared to traditional entanglement distribution routing designs.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104156"},"PeriodicalIF":7.7,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143592976","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

Heuristic and approximate Steiner tree algorithms for ensuring network connectivity in mobile wireless sensor networks

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-06 DOI: 10.1016/j.jnca.2025.104155

Nguyen Van Son , Nguyen Thi Hanh , Trinh The Minh , Huynh Thi Thanh Binh , Nguyen Xuan Thang

{"title":"Heuristic and approximate Steiner tree algorithms for ensuring network connectivity in mobile wireless sensor networks","authors":"Nguyen Van Son , Nguyen Thi Hanh , Trinh The Minh , Huynh Thi Thanh Binh , Nguyen Xuan Thang","doi":"10.1016/j.jnca.2025.104155","DOIUrl":"10.1016/j.jnca.2025.104155","url":null,"abstract":"<div><div>Connectivity problems are among the most challenging issues in Mobile Wireless Sensor Networks (MWSNs). Ensuring connectivity in such networks means finding network configurations in which all mobile sensors can connect to a base station during data gathering events. This paper considers MWSNs in which a minimal number of relay nodes need to be placed in order to maintain connectivity. Two algorithms are proposed: AST (Approximation Steiner Tree) is an approximate algorithm with a ratio of <span><math><mrow><mn>2</mn><mo>×</mo><mi>o</mi><mi>p</mi><mi>t</mi><mo>+</mo><mi>O</mi><mrow><mo>(</mo><mi>K</mi><mo>×</mo><mi>N</mi><mo>)</mo></mrow></mrow></math></span> (where <span><math><mrow><mi>K</mi><mo>×</mo><mi>N</mi></mrow></math></span> is the number of nodes on the time-flattened domain) and CBAST (Cluster-Based on the Approximation Steiner Tree algorithm) is a highly effective heuristic. Both algorithms focus on optimal Steiner Tree construction to produce high-quality solutions. AST is an approximation based on 3-point Steiner Trees, while CBAST forms clusters of static components and uses a 2-approximation algorithm to maintain connectivity in each cluster. Experiments on a large number of generated instances are performed to compare AST and CBAST with existing state-of-the-art heuristics. Our results show that CBAST significantly outperforms baseline methods while also reducing computation time and energy consumption.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104155"},"PeriodicalIF":7.7,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611370","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

Device-to-device communication in 5G heterogeneous network based on game-theoretic approaches: A comprehensive survey

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-03 DOI: 10.1016/j.jnca.2025.104152

Rana Zeeshan Ahmad , Muhammad Rizwan , Muhammad Jehanzaib Yousuf , Mohammad Bilal Khan , Ahmad Almadhor , Thippa Reddy Gadekallu , Sidra Abbas

{"title":"Device-to-device communication in 5G heterogeneous network based on game-theoretic approaches: A comprehensive survey","authors":"Rana Zeeshan Ahmad , Muhammad Rizwan , Muhammad Jehanzaib Yousuf , Mohammad Bilal Khan , Ahmad Almadhor , Thippa Reddy Gadekallu , Sidra Abbas","doi":"10.1016/j.jnca.2025.104152","DOIUrl":"10.1016/j.jnca.2025.104152","url":null,"abstract":"<div><div>In the evolution of Fifth-Generation (5G) oriented wireless communication technology, the conventional wireless communication performance indicators, including network capacity, spectrum efficiency, and Quality of Services (QoS), need to be continuously improved to optimize the utilization of the wireless spectrum. As a key candidate technology for 5G, Device-to-Device (D2D) communication improves system performance, enhances user experience, and expands cellular communication applications. D2D communication provides a better quality of services with minor communication delays, improving overall network performance, efficient utilization of network resources, and enhanced network capacity by utilizing short-distance communication between devices in close proximity. D2D communication technology has recently received widespread attention due to its promising nature. This survey comprehensively reviews D2D communication and the techniques involved in different phases of successful D2D communication. In addition, this survey paper also presents an extensive review of proposed solutions based on game-theoretic approaches aiming to optimize the performance of D2D communication in 5G. The major objectives of this survey paper are to thoroughly analyze current developments in D2D communication and review game theory applications in D2D communication. This survey also identifies challenges in D2D communication, opens issues, and suggests future research areas.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104152"},"PeriodicalIF":7.7,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143563516","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

Digital twins-enabled game theoretical models and techniques for metaverse Connected and Autonomous Vehicles: A survey

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-03-01 DOI: 10.1016/j.jnca.2025.104138

Anjum Mohd Aslam , Rajat Chaudhary , Aditya Bhardwaj , Neeraj Kumar , Rajkumar Buyya

{"title":"Digital twins-enabled game theoretical models and techniques for metaverse Connected and Autonomous Vehicles: A survey","authors":"Anjum Mohd Aslam , Rajat Chaudhary , Aditya Bhardwaj , Neeraj Kumar , Rajkumar Buyya","doi":"10.1016/j.jnca.2025.104138","DOIUrl":"10.1016/j.jnca.2025.104138","url":null,"abstract":"<div><div>The popularity of information and communication technology in automobiles has led to the next generation of smart vehicles known as Connected and Autonomous Vehicles (CAVs). The advent of the CAVs has rapidly emerged as an essential component of Intelligent Transportation Systems (ITS) due to the usage of advanced technologies for autonomous navigation, sensing, and improved vehicle safety. Moreover, during this era, Metaverse, often known as an embodied version of the Internet, aims to create a fully immersive and self-sustaining virtual shared space where individuals can live and interact through digital avatars. Recent technological breakthroughs like Web 3.0, 6G networks, extended reality, artificial intelligence, edge computing, and blockchain propel the Metaverse from science fiction to a near-future reality. Moreover, an integral component enabling this transformation is Digital Twins (DTs), which play an essential role in establishing the communication link between the two realms. This article comprehensively analyzes a detailed assessment of the CAVs-assisted Digital Twin-enabled game theoretical models and techniques used in CAVs Metaverse. Moreover, we explore the decentralized and autonomous nature of blockchain technology, making it an ideal platform for CAVs for securing financial transactions in the Metaverse, fostering trust and authenticity. Finally, we discuss open issues and future research opportunities for Digital Twin-enabled CAV Metaverse systems.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104138"},"PeriodicalIF":7.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621361","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

An optimal three-tier prioritization-based multiflow scheduling in cloud-assisted smart healthcare

IF 7.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2025-02-25 DOI: 10.1016/j.jnca.2025.104143

Sarthak , Anshul Verma , Pradeepika Verma

{"title":"An optimal three-tier prioritization-based multiflow scheduling in cloud-assisted smart healthcare","authors":"Sarthak , Anshul Verma , Pradeepika Verma","doi":"10.1016/j.jnca.2025.104143","DOIUrl":"10.1016/j.jnca.2025.104143","url":null,"abstract":"<div><div>Internet of Things is significantly advancing the development of modern interconnected networks. Coordinated with cloud computing, this technology becomes even more powerful, cost-effective, and reliable. These advancements are rapidly being integrated into modern healthcare through innovations such as smart ambulances, remote monitoring systems, and smart hospitals, enhancing tracking, analysis, and alerting capabilities. However, these innovations also bring challenges, particularly in task allocation and resource management for safety-critical systems that must meet stringent quality of service while efficiently utilizing resources. This paper introduces a new heuristic Three-Tier Prioritization based Multiflow Scheduling (TTPMS) approach for smart healthcare in cloud, utilizing the adaptive multi-criteria decision-making. The proposed TTPMS algorithm prioritizes tasks across three levels, considering factors such as urgency, deadlines, budget, and impact value within the workflow, and then dynamically selects the most suitable virtual machine for allocation. Performance comparisons were made against traditional approaches like the Prioritized Sorted Task-Based Algorithm (PSTBA) and the Max–Min algorithm. Experiments conducted using the Eclipse IDE with Java, demonstrated that the proposed approach significantly outperforms traditional algorithms across multiple metrics, including success rates for deadlines and budgets, as well as the resource utilization. It achieved a 98% deadline adherence rate, outperforming Max–Min (93%) and PSTBA (60%). Additionally, TTPMS surpassed budget adherence metrics, achieving a 76% success rate compared to PSTBA (72%) and Max–Min (70%). For combined adherence to both deadlines and budgets, TTPMS achieved a 74% success rate, outperforming PSTBA (33%) and Max–Min (63%). These results highlight the effectiveness of TTPMS in scheduling the healthcare applications.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104143"},"PeriodicalIF":7.7,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143519008","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