Computer Science Review最新文献

{"title":"A comprehensive review on machine learning-based VPN detection: Scenarios, methods, and open challenges","authors":"Alejandro Guerra-Manzanares ,&nbsp;Maurantonio Caprolu ,&nbsp;Roberto Di Pietro","doi":"10.1016/j.cosrev.2025.100781","DOIUrl":"10.1016/j.cosrev.2025.100781","url":null,"abstract":"<div><div>Virtual Private Networks (VPNs) are an essential tool to protect user privacy and enforce secure communications over the Internet. However, they can also be misused to bypass legit network security mechanisms and hence access otherwise restricted content. These reasons, combined with the fact that VPN supporting technology has continuously evolved—reaching quite a relevant level of sophistication—make detecting VPN traffic a vested research issue for both academia and industry. In this paper, we provide a comprehensive review of machine learning-based (ML) solutions for VPN traffic detection. In particular, we start with framing the problem and identifying the main scenarios and related adversary models. Then, we provide a thorough analysis of the related literature and state-of-the-art in ML methodologies for VPN detection, identifying research gaps and unresolved challenges. In particular, we show that the vast majority of the current solutions rely on a specific dataset that suffers from a few severe limitations, hence questioning the validity of reported results when applied to real use case scenarios. Finally, we summarize existing knowledge highlighting common mistakes and providing guidelines as well as future research directions. To the best of our knowledge, this is the first paper that provides a deep dive into ML methodologies for VPN detection, showing current pitfalls, providing actionable recommendations, as well as suggesting research directions.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100781"},"PeriodicalIF":13.3,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration of SDN into UAV, edge computing, & Blockchain: A review, challenges, & future directions","authors":"Tejas M. Modi ,&nbsp;Kuna Venkateswararao ,&nbsp;Pravati Swain","doi":"10.1016/j.cosrev.2025.100790","DOIUrl":"10.1016/j.cosrev.2025.100790","url":null,"abstract":"<div><div>Software Defined Network(SDN) is an advanced architecture that enhances the centralized access of the network topology through a central controller. Emerging networking mechanisms provide novel advanced architectures that enhance the application usage scenarios. Emerging networking mechanisms, i.e., Edge computing, Unmanned Aerial Vehicle (UAV) systems, and Blockchain, are new techniques that generate various communication models to provide secure and virtual access to the network entities. However, the UAV and edge computing systems cannot handle the high traffic congestion in the network. The system must offload the data computation to other devices in these scenarios. The offloading process requires a central authority to manage task computation and available resources in the system. Thus, SDN can provide a central controller to handle the resources in the UAV and edge computing system.</div><div>Meanwhile, SDN lacks security, and Blockchain needs to manage the trusted third-party entities in the system. For these problems, the SDN and Blockchain provide resilience to each other in architectural advancements. This proposed survey presents state-of-the-art fusion systems where SDN is integrated into emerging networking mechanisms. The main objective is to represent the integration of SDN into UAV, Edge Computing, and Blockchain systems for different domains, i.e., routing, resource management, task offloading, network management, and security. Moreover, the survey represents the various simulation tools and performance parameters of fusion architectures. Furthermore, the survey illustrates challenges, open issues, and future directions in the next generation of networking systems.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100790"},"PeriodicalIF":13.3,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144654469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep anomaly detection for time series: A survey","authors":"Xudong Jia,&nbsp;Peng Xun,&nbsp;Wei Peng,&nbsp;Baokang Zhao,&nbsp;Haojie Li,&nbsp;Chiran Shen","doi":"10.1016/j.cosrev.2025.100787","DOIUrl":"10.1016/j.cosrev.2025.100787","url":null,"abstract":"<div><div>The cyberspace environment has evolved into a complex ecosystem, generating vast amounts of diverse time series data from various devices, systems, and software. Detecting anomalies in these massive, multi-source datasets is critical for ensuring system reliability and security. This paper provides a comprehensive review of deep learning approaches for time series anomaly detection. We systematically classify existing methods into six categories based on their objective functions: forecasting models, reconstruction models, generative models, density models, contrastive models, and hybrid models. For each category, we analyze their advantages, disadvantages, and architectural variations to guide researchers in selecting appropriate approaches for specific problems. We further summarize applications across multiple domains including network services, cyber–physical systems, smart grids, smart cities, and healthcare, providing valuable insights into practical implementations. The paper also organizes commonly used public datasets with their key characteristics and examines evaluation metrics ranging from traditional point-level assessments to advanced sequence-adaptive frameworks. Finally, we discuss emerging challenges and promising research directions, including data augmentation strategies, model robustness improvements, generalization capabilities, applications of foundation models and large language models, autoML frameworks, and lightweight model designs. This survey offers a systematic framework for understanding the current landscape of deep time series anomaly detection and provides clear pathways for advancing the field to address real-world challenges.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100787"},"PeriodicalIF":13.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The computing continuum: Past, present, and future","authors":"Luiz F. Bittencourt ,&nbsp;Roberto Rodrigues-Filho ,&nbsp;Josef Spillner ,&nbsp;Filip De Turck ,&nbsp;José Santos ,&nbsp;Nelson L.S. da Fonseca ,&nbsp;Omer Rana ,&nbsp;Manish Parashar ,&nbsp;Ian Foster","doi":"10.1016/j.cosrev.2025.100782","DOIUrl":"10.1016/j.cosrev.2025.100782","url":null,"abstract":"<div><div>The development of network-connected computing resources has led to various computing paradigms over the years, each bringing its own set of challenges for creating efficient distributed systems. Currently, there is an increasing need to integrate the evolving Internet of Things (IoT) with the established Cloud infrastructure. This integration often requires adding intermediate layers to address Cloud limitations such as latency, bandwidth, security, cost, and control. This configuration, known as the computing continuum, involves a diverse array of distributed devices with unique characteristics working together to meet the demands of both current and emerging applications. This paper explores the path that has led to the development of the computing continuum, offering a technology-agnostic definition from a historical perspective. It also examines applications that can benefit from the computing continuum and identifies research challenges that need to be addressed to fully realize its potential.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100782"},"PeriodicalIF":13.3,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144588383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Autoscaling techniques in cloud-native computing: A comprehensive survey","authors":"Byeonghui Jeong,&nbsp;Young-Sik Jeong","doi":"10.1016/j.cosrev.2025.100791","DOIUrl":"10.1016/j.cosrev.2025.100791","url":null,"abstract":"<div><div>Autoscaling, the core technology of cloud-native computing, dynamically adjusts computing resources as per application load fluctuations in order to improve scalability, cost efficiency, and performance continuity. By doing so, autoscaling enables widespread adoption of cloud-native computing across various industries; consequently, autoscaling techniques are critical for supporting the cloud-native paradigm. This study aims to provide a comprehensive survey of cloud-native autoscaling techniques, offering a unified understanding of current approaches and identifying unresolved issues. First, autoscaling algorithms and mechanisms are each classified into three types. Through this classification framework, a wide range of scaling algorithms, from threshold-based reactive policies to artificial intelligence (AI)-based proactive policies, are examined, and their respective advantages and limitations are analyzed. Next, the study comprehensively investigates and summarizes the experimental environments, datasets, and performance metrics used for evaluating autoscaling techniques. Furthermore, it systematically discusses key considerations for optimizing autoscaling techniques across the lifecycle of cloud-native applications by dividing the process into three distinct stages. In addition, this study provides a comprehensive review of cyberattacks that exploit autoscaling and the corresponding mitigation strategies. Finally, it discusses open issues, future directions, and research opportunities related to autoscaling in cloud-native computing.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100791"},"PeriodicalIF":13.3,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144588382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comprehensive review of cybersecurity vulnerabilities, threats, and solutions for the Internet of Things at the network-cum-application layer","authors":"Abdul Razaque ,&nbsp;Salim Hariri ,&nbsp;Abrar M. Alajlan ,&nbsp;Joon Yoo","doi":"10.1016/j.cosrev.2025.100789","DOIUrl":"10.1016/j.cosrev.2025.100789","url":null,"abstract":"<div><div>The proliferation of smart homes, smart logistics, and other technologies has expedited the expansion of Internet-of-Things (IoT) devices. This expansion has heightened the complexity of associated security challenges. Despite extensive research on IoT security, several studies fail to provide a comprehensive examination of both the network and application layers. This is particularly applicable to real-time and mission-critical settings. This review addresses that deficiency by offering a systematic review of IoT across five tiers. It concentrates on the application layer, categorizing it into three domains: real-time control systems, scientific decision-making systems, and query/scan search systems. The study examines vulnerabilities, attack vectors, and security measures in real-time control and query/scan systems. It examines how emerging technologies such as artificial intelligence (AI), Software Defined Networking (SDN), and fog/edge computing can enhance security via improved context awareness and access management. The study ultimately presents recommendations and suggests enhancements to foster trust, scalability, and enhanced security in contemporary IoT systems.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100789"},"PeriodicalIF":13.3,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Facial privacy in the digital era: A comprehensive survey on methods, evaluation, and future directions","authors":"Miaomiao Wang ,&nbsp;Sheng Li ,&nbsp;Xinpeng Zhang ,&nbsp;Guorui Feng","doi":"10.1016/j.cosrev.2025.100785","DOIUrl":"10.1016/j.cosrev.2025.100785","url":null,"abstract":"<div><div>With the advancement of computer vision technology and smart devices, images and videos containing facial information are increasingly shared on social media, making it easier for facial data to be collected and misused. As sensitive biometric data, once facial information is leaked, it may cause irreversible damage to personal privacy. Ensuring the security of facial information while benefiting from technological conveniences has become a critical research area. Many surveys have summarized existing protection measures, which often focus on specific issues or are oriented toward particular technologies, so existing methods have not been comprehensively summarized. In this paper, we categorize facial privacy-preserving methods into four paradigms: appearance-guided, identity-guided, reversible, and privacy-preserving for facial recognition systems. We offer an in-depth review of the most representative methods, emphasizing their advantages and functional characteristics. Additionally, we present commonly used datasets and evaluation metrics and analyze the performance of current methods. Finally, we discuss the challenges and opportunities for practical applications in facial privacy protection, offering insights for future research.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100785"},"PeriodicalIF":13.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Denoising and completion filters for human motion software: A survey with code","authors":"Enrico Martini,&nbsp;Andrea Calanca,&nbsp;Nicola Bombieri","doi":"10.1016/j.cosrev.2025.100780","DOIUrl":"10.1016/j.cosrev.2025.100780","url":null,"abstract":"<div><div>Software platforms for human motion analysis are increasingly utilized across various fields, from Healthcare to Industry 5.0. However, the inherent inaccuracies of these platforms often lead to noisy observations of human poses or periods of missing information. As a result, data filtering for denoising or completion is a fundamental step before data analysis. Over the years, different techniques have been proposed, from general-purpose solutions based on low-pass filters to more advanced and embedded approaches based on state observers rather than deep learning. This survey presents the current state-of-the-art filtering solutions for denoising and completing data generated by software platforms for human motion analysis. It focuses on 3D positional data extrapolated through marker-based or marker-less motion capture systems. The survey proposes a concise taxonomy based on filter technology and application assumptions. For each class, it summarizes the basic concepts and reports application feedback collected from the literature. The survey also includes implementation codes or links to the authors’ original codes, enabling readers to quickly reproduce all the algorithms in different experimental settings (<span><span>https://github.com/PARCO-LAB/mocap-refinement</span><svg><path></path></svg></span>).</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100780"},"PeriodicalIF":13.3,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic literature review on cross-language source code clone detection","authors":"Asra Sulaiman Alshabib ,&nbsp;Sajjad Mahmood ,&nbsp;Mohammad Alshayeb","doi":"10.1016/j.cosrev.2025.100786","DOIUrl":"10.1016/j.cosrev.2025.100786","url":null,"abstract":"<div><h3>Context</h3><div>Cross-language code Clone Detection (CLCCD) is crucial to maintaining consistency and minimizing redundancy in modern software development, where similar code may appear in different projects written in various programming languages. While previous reviews have explored code clone detection in general, none have exclusively focused on CLCCD.</div></div><div><h3>Objective</h3><div>This study aims to bridge this gap by reviewing the existing CLCCD approaches, focusing on detection techniques, preprocessing methods, feature extraction approaches, datasets, and evaluation metrics used.</div></div><div><h3>Method</h3><div>A systematic literature review (SLR) was conducted, analyzing 26 studies published in journals, conferences, and workshops until May 2025. Both quantitative and qualitative data were systematically analyzed to derive the findings.</div></div><div><h3>Results</h3><div>CLCCD has evolved from traditional techniques to deep learning models, but fully automated tools remain unavailable. Parsing (73 %), normalization (35 %), and tokenization (27 %) are widely used preprocessing techniques in CLCCD methods. Most studies (38.5 %) employ hybrid feature extraction, which combines tree-based and graph-based methods to capture code structure and semantics. However, the datasets primarily sourced from programming competition platforms lack diversity and standardization. Performance evaluation largely relies on metrics like precision, recall, and F1-score, while incorporating additional evaluation metrics could provide more insights into detection performance.</div></div><div><h3>Conclusion</h3><div>This SLR summarizes current CLCCD research, highlighting advancements and challenges. Significant gaps include the absence of diverse and standardized datasets and the limited exploration of advanced feature extraction techniques. Future research should focus on creating better datasets, adopting novel detection techniques, and exploring feature extraction methods to improve CLCCD performance for modern multi-language systems.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100786"},"PeriodicalIF":13.3,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144491940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Edge-AI empowered Cyber-Physical Systems: A comprehensive review on performance analysis","authors":"Raj Kumar Baliyar Singh,&nbsp;K Hemant Kumar Reddy","doi":"10.1016/j.cosrev.2025.100769","DOIUrl":"10.1016/j.cosrev.2025.100769","url":null,"abstract":"<div><div>Cyber-Physical Systems (CPS) are integral to the advancement of smart technologies, combining computational elements with physical processes. Edge computing has emerged as a pivotal enabler for CPS, addressing the latency, energy, accuracy, and bandwidth issues inherent in cloud-based solutions. This comprehensive survey examines the critical performance parameters of Edge-assisted Cyber-Physical Systems (EaCPS). The study explores performance metrics such as latency, energy efficiency, accuracy, scalability, security, and reliability. It highlights the interplay between these parameters and the operational efficiency of EaCPS. It primarily focuses on traditional methods and models used in CPS, examining their evolution and performance, particularly in the context of Edge computing. In addition, it evaluates the performance of various CPSs integrated with AI capabilities. The review also discusses current research trends, challenges, and future directions, providing a holistic understanding of the optimization strategies necessary to improve EaCPS performance.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100769"},"PeriodicalIF":13.3,"publicationDate":"2025-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144479988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}