Computer Science Review最新文献

{"title":"A survey on decentralized identity management systems","authors":"Jia Xian,&nbsp;Lin You,&nbsp;Qifei Yi,&nbsp;Jixiang Wang,&nbsp;Gengran Hu","doi":"10.1016/j.cosrev.2025.100811","DOIUrl":"10.1016/j.cosrev.2025.100811","url":null,"abstract":"<div><div>Digital identity is a crucial tool in the field such as healthcare, education and government. It serves as the foundation for establishing presence in cyberspace. With the increasing demands for security, control and portability, digital identity has evolved through four stages: centralized, federated, user-centric and self-sovereign identity. Among these, the decentralized identity represents the self-sovereign identity stage, emphasizing the idea of the user fully control over the user’s identity. Blockchain, as the key technology enabling decentralization, provides robust support for the decentralized identity through its transparent, distributed and immutable characteristics. We investigate the blockchain-based Decentralized Identity Management Systems (DIDMS), analyzing their advantages over the previous systems in terms of the enhanced control, privacy, and security. We propose a four-phase architecture for the DIDMS, detailing how the users can achieve self-management through the DIDMS without relying on the centralized entities. Furthermore, this investigation compares the various solutions with the core practical properties, explores the relationships between these features, and summarizes the evaluation criteria for the DIDMS. Additionally, the work evaluates both classical and cutting-edge DIDMS solutions and discusses the challenges faced by the DIDMS, along with potential solutions, providing direction for future research and practice.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100811"},"PeriodicalIF":12.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922624","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":"Low-light multimodal object detection: A survey","authors":"Gang Li ,&nbsp;Yonggui Wang ,&nbsp;Bin He ,&nbsp;Tao Pang ,&nbsp;Mingke Gao","doi":"10.1016/j.cosrev.2025.100804","DOIUrl":"10.1016/j.cosrev.2025.100804","url":null,"abstract":"<div><div>This survey aims to gain an in-depth understanding of the current state of research on multimodal object detection in low-light environments. Firstly, we introduce the background of multimodal object detection in low-light environments, discuss the challenges faced by this task, and provide an overview of existing related review literature. Secondly, we comprehensively introduce the multimodal sensor combinations and their specific models, benchmark datasets, and evaluation criteria currently applicable to multimodal object detection tasks in low-light environments. In addition, we conduct a comprehensive investigation of multimodal detection methods such as visible-infrared and visible-LiDAR, as well as other multimodal detection methods, and conduct in-depth analysis and discussion on the potential and challenges of each method. Finally, we present a quantitative comparison of the most advanced methods on widely used benchmark datasets and discuss research trends, important issues, and future research directions.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100804"},"PeriodicalIF":12.7,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144922621","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 decade systematic review of fusion techniques in financial market prediction","authors":"Soheila Mehrmolaei,&nbsp;Mohammad Saniee Abadeh","doi":"10.1016/j.cosrev.2025.100813","DOIUrl":"10.1016/j.cosrev.2025.100813","url":null,"abstract":"<div><div>Financial markets are structured systems that facilitate investment, trading, and economic growth at both global and local levels. Accurate and reliable prediction in these markets is essential for making profitable decisions. However, the inherent complexity of financial markets, influenced by numerous external factors, makes it difficult to perform analysis and forecasting. In this context, fusion techniques have emerged as a strong and well-known approach, integrating data and features from multiple sources to enhance prediction accuracy. This paper presents a systematic review of studies on fusion techniques in financial market prediction, covering research published between 2016 and 2025. The primary objective is to provide a comprehensive understanding of the role of fusion techniques in financial market prediction from both macro and micro perspectives. To achieve this, we categorize fusion techniques based on level of integration, analyzing their benefits, limitations, and applications. Additionally, we discuss the necessity of fusion approaches, open challenges, and potential future advancements in this domain. Our review emphasizes the growing adoption of multimodal text data fusion using large language models (LLMs) as a promising trend to enhance prediction reliability. Also, we identify key research directions and emerging trends that are expected to shape the future development of fusion-based financial market prediction methods.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100813"},"PeriodicalIF":12.7,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144912513","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":"Routing optimization strategies in data center networks: A survey","authors":"Bin Xu ,&nbsp;Yong Liu ,&nbsp;Qian Meng ,&nbsp;Ben Wang","doi":"10.1016/j.cosrev.2025.100808","DOIUrl":"10.1016/j.cosrev.2025.100808","url":null,"abstract":"<div><div>As a critical component of cloud and distributed computing infrastructures, optimizing routing strategies in Data Center Networks (DCNs) is crucial for ensuring high bandwidth, low latency, high reliability, and energy efficiency. However, traditional routing policies encounter significant challenges in addressing dynamic traffic patterns, cross-domain transmissions, and the increasing demands for green computing, necessitating systematic analysis and innovative optimization. This paper presents a comprehensive review and classification of existing routing strategies, addressing the gap in current research regarding the applicability and systematic comparison between intra-DCN and inter-DCN environments. Notably, intra-DCNs and inter-DCNs differ significantly in their architectural characteristics, operational requirements, and functional objectives, which necessitates tailored routing strategies for each domain. We proposed a novel framework for classifying routing policies. For intra-DCNs, we examined core policies across six dimensions: load optimization, traffic scheduling, congestion control, intelligent optimization, fault-tolerant, and energy efficiency. For inter-DCNs, the analysis covers routing strategies focused on load balancing, traffic scheduling, fault-tolerant, energy efficiency, and intelligent optimization. Through comparative analysis, this paper underscores the strengths and limitations of existing strategies, providing researchers with a comprehensive framework for advancing this field. Additionally, we outlined future research directions. The contribution of this paper lies in offering theoretical support and practical guidance for routing strategy design in both academia and industry, promoting the development of efficient, low-latency data transmission technologies, and guiding DCNs optimization in emerging scenarios such as 5G and edge computing.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100808"},"PeriodicalIF":12.7,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144906838","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":"From past to present: A survey of malicious URL detection techniques, datasets and code repositories","authors":"Ye Tian ,&nbsp;Yanqiu Yu ,&nbsp;Jianguo Sun ,&nbsp;Yanbin Wang","doi":"10.1016/j.cosrev.2025.100810","DOIUrl":"10.1016/j.cosrev.2025.100810","url":null,"abstract":"<div><div>Malicious URLs persistently threaten the cybersecurity ecosystem, by either deceiving users into divulging private data or distributing harmful payloads to infiltrate host systems. The detection of malicious URLs is a protracted arms race between defenders and attackers. Gaining timely insights into the current state of this ongoing battle holds significant importance. However, existing reviews suffer from four critical limitations: 1) Their reliance on algorithm-centric taxonomies obscures understanding of how detection approaches exploit specific modal information channels; 2) They fail to incorporate pivotal LLM/Transformer-based defenses; 3) No open-source implementations are collected to facilitate benchmarking; 4) Insufficient dataset coverage.</div><div>This paper presents a comprehensive review of malicious URL detection technologies, systematically analyzing methods from traditional blacklisting to advanced deep learning approaches (e.g., Transformer, GNNs, and LLMs). Unlike prior surveys, we propose a novel modality-based taxonomy that categorizes existing works according to their primary data modalities (e.g., lexical URL features, HTML structure, JavaScript behavior, visual layout).For instance, we group models that parse DOM trees and extract HTML tag paths into the HTML modality, while those using rendered webpage screenshots are classified under the visual modality. This taxonomy reveals how distinct input channels inform model design, offering new perspectives that are obscured in algorithm-based classifications. This hierarchical classification enables both rigorous technical analysis and clear understanding of multimodal information utilization. Furthermore, to establish a profile of accessible datasets and address the lack of standardized benchmarking (where current studies often lack proper baseline comparisons), we curate and analyze two key resources: 1) publicly available datasets (2016–2024), and 2) open-source implementations from published works (2013–2025). To facilitate cross-method comparison and support future benchmarking efforts, we compile a comparative table summarizing key performance metrics (e.g., Accuracy, F1 Score, AUC) as reported in the original works or open-source repositories. While no formal evaluation protocol is proposed, this effort provides a practical reference point and highlights the need for more standardized benchmarking practices in malicious URL detection research. The review concludes by examining emerging challenges and proposing actionable directions for future research. We maintain a GitHub repository for ongoing curation of datasets and open-source implementations: <span><span>https://github.com/sevenolu7/Malicious-URL-Detection-Open-Source/tree/master</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100810"},"PeriodicalIF":12.7,"publicationDate":"2025-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144902472","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":"Polynomial property testing","authors":"Lior Gishboliner ,&nbsp;Asaf Shapira","doi":"10.1016/j.cosrev.2025.100806","DOIUrl":"10.1016/j.cosrev.2025.100806","url":null,"abstract":"<div><div>Property testers are fast, randomized “election polling”-type algorithms that determine if an input (e.g., graph or hypergraph) has a certain property or is <span><math><mi>ɛ</mi></math></span>-far from the property. It is known that many properties can be tested with query complexity that depends only on the error parameter <span><math><mi>ɛ</mi></math></span> (and not on the size of the input), but the current bounds on the query complexity grow extremely quickly as a function of <span><math><mfrac><mrow><mn>1</mn></mrow><mrow><mi>ɛ</mi></mrow></mfrac></math></span>. Which properties can be tested <em>efficiently</em>, i.e., with <span><math><mrow><mtext>poly</mtext><mrow><mo>(</mo><mn>1</mn><mo>/</mo><mi>ɛ</mi><mo>)</mo></mrow></mrow></math></span> queries? This survey presents the state of knowledge on this general question, focusing on the dense graph model of property testing. Several key open problems are presented.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100806"},"PeriodicalIF":12.7,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893235","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 review of background, methods, limitations and opportunities of knowledge graph completion","authors":"Daiyi Li ,&nbsp;Yaoyao Liang ,&nbsp;Shenyi Qian ,&nbsp;Huaiguang Wu ,&nbsp;Wei Jia ,&nbsp;Yilong Fu ,&nbsp;Yifan Sun","doi":"10.1016/j.cosrev.2025.100809","DOIUrl":"10.1016/j.cosrev.2025.100809","url":null,"abstract":"<div><div>Knowledge graph completion (KGC), as a pivotal technology for extracting hidden knowledge from large-scale data, has evolved into a systematic research framework through the development of knowledge graph (KG) technology in recent years. To address the many challenges faced by current research, this study systematically reviews the fundamental theories and methodological systems in the field of KGC, grouping them into four categories: embedding-based, path-based, neural network-based, and large language model (LLM)-based approaches. Current research indicates that traditional closed-domain KGC relies on standard KG embedding or relational path models, which remain effective for completing structured data. However, there are notable limitations in handling unseen entities and relations in open scenarios. With breakthroughs in neural networks and LLMs, open-domain KGC has begun to emerge, although a lack of systematic analysis and classification of model architectures still persists. To address this gap, this review conducts a multi-dimensional academic investigation, clarifying the foundational research landscape and core methodological distinctions, establishing a model classification framework that spans both closed and open domains and integrating mainstream dataset resources within the field. Furthermore, the review explores the challenges and future directions of technological development, including critical issues such as complex knowledge reasoning, improvements in domain adaptability improvement, and the deep integration of LLMs with KGs, providing theoretical foundations and practical references to guide subsequent research efforts.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100809"},"PeriodicalIF":12.7,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864577","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":"Advancing IoT-driven WSNs with context-aware routing: A comprehensive review","authors":"Ahmed M. Khedr ,&nbsp;Oruba Alfawaz ,&nbsp;Pravija Raj P.V. ,&nbsp;Walid Osamy","doi":"10.1016/j.cosrev.2025.100803","DOIUrl":"10.1016/j.cosrev.2025.100803","url":null,"abstract":"<div><div>With the increasing complexity of dynamic and heterogeneous IoT-driven Wireless Sensor Networks (WSNs), context-aware routing has emerged as a promising approach to optimize network performance. These protocols improve Quality of Service (QoS), increase network lifespan, and improve energy efficiency by utilizing contextual data. However, they remain underexplored compared to traditional routing schemes. This survey presents the first comprehensive review in this area, addressing key research gaps by examining their evolution, methodologies, and performance over the past two decades. A novel classification framework is introduced, categorizing the protocols based on operational context and network characteristics, providing a structured view of their design. Moreover, diverse context-aware strategies are assessed, highlighting their benefits and limitations. It also outlines open challenges, emerging application areas, and future research opportunities. Key findings reveal that the context-aware proactive methods are the main focus of the majority of current research on both static and dynamic environments, and are commonly assessed using metrics including packet delivery, delay, and energy usage. In contrast, reactive and hybrid methods have received less attention, especially in terms of packet delivery, delay, and throughput. The Context-Aware Clustering Hierarchy (CACH) is found to reduce the energy consumption by 58.8% compared to the conventional Low-Energy Adaptive Clustering Hierarchy (LEACH) based models. CACH retains energy in 50% of nodes, while LEACH depletes 70%. Similarly, the Context-Aware RPL Routing (CA-RPL) adapts to node mobility with 50% less power consumption, achieving a packet delivery ratio of 85%–90% under low mobility and over 80% under high speed and density, enhancing both network lifespan and QoS. By providing critical insights and comparative evaluations, this study serves as a valuable resource for researchers and practitioners, guiding future innovations in this field.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100803"},"PeriodicalIF":12.7,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842058","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":"Hyperbolic geometric graph representation learning: A survey","authors":"Siman Wang ,&nbsp;Xu Chen ,&nbsp;Yongjun Jing ,&nbsp;Shuyang Wang","doi":"10.1016/j.cosrev.2025.100800","DOIUrl":"10.1016/j.cosrev.2025.100800","url":null,"abstract":"<div><div>Graph representation learning is a crucial technology, which converts graph data into low-dimensional vector representations and significantly enhances various machine learning tasks. Traditional Euclidean space often faces the curse of dimensionality when representing graph structures, especially for graph data possessing complex relationships. Hyperbolic geometry, as a form of non-Euclidean geometry, has superior capabilities to more accurately capture the graph data of nonlinear relationships and hierarchical structures, making it an effective tool for handling complex graph data. To stimulate future research, this paper presents a comprehensive reviews of literature around the graph representation learning in hyperbolic geometry. We offer a new taxonomy of hyperbolic graph representation methods by embedding graph data with different structures into various geometric spaces, including hyperbolic space graph representation learning and spatial fusion graph representation learning. Moreover, it emphasizes the applications of hyperbolic geometric representation learning across various domains, such as knowledge graphs, recommendation systems, biomolecular analysis, and natural language processing, while also exploring potential future research directions.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100800"},"PeriodicalIF":12.7,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144830990","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":"Robust defense mechanisms for protecting Wireless Sensor Networks from Denial-of-Service Threats, A comprehensive in-depth analysis","authors":"Walid Osamy ,&nbsp;Ahmed M. Khedr ,&nbsp;Pravija Raj P.V. ,&nbsp;Bader Alwasel ,&nbsp;Ahmed Salim","doi":"10.1016/j.cosrev.2025.100797","DOIUrl":"10.1016/j.cosrev.2025.100797","url":null,"abstract":"<div><div>Wireless Sensor Networks (WSNs) are inherently vulnerable due to their reliance on wireless communication and often unattended deployment. These vulnerabilities make them frequent targets of Denial-of-Service (DoS) attacks, which can significantly disrupt network operations and degrade overall functionality. This study presents a comparative analysis of the resilience of three core WSN clustering paradigms: Deterministic, Probabilistic, and Hybrid models, against a range of DoS attack scenarios. Six distinct DoS attack types, including Black Hole, various Gray Hole variants, Flooding, and Scheduling attacks are examined, along with an analysis of the impact of varying cluster head rotation periods. We provide an in-depth understanding of the impact of these attacks by examining key performance indicators like Packet Delivery Ratio (PDR), network lifetime, throughput, and energy consumption to support the development of innovative strategies for enhancing resilience. The analysis reveals that, while each clustering approach has particular advantages, there is no generic solution suitable for all scenarios. To quantify the impact of DoS attacks on clustering models, we introduced the Attack Impact Score (AIS), which measures the degradation of critical performance metrics. The Deterministic model tends to be more vulnerable to aggressive attack scenarios, whereas Probabilistic and Hybrid models show slightly greater resilience under specific conditions. However, none of the models demonstrated complete robustness when facing sophisticated attacks. Further, two-way ANOVA analysis were performed to evaluate the attack impact on key performance metrics, providing deeper insights into overall resilience of the WSN clustering architectures to various DoS attack scenarios.</div></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":"58 ","pages":"Article 100797"},"PeriodicalIF":12.7,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144827343","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}