Computer Networks最新文献_第2页

PDMA: Efficient and privacy-preserving dynamic task assignment with multi-attribute search in crowdsourcing 基于多属性搜索的众包动态任务分配算法

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-15 DOI: 10.1016/j.comnet.2025.111279

Haiyong Bao , Ronghai Xie , Zhehong Wang , Lu Xing , Hong-Ning Dai

{"title":"PDMA: Efficient and privacy-preserving dynamic task assignment with multi-attribute search in crowdsourcing","authors":"Haiyong Bao , Ronghai Xie , Zhehong Wang , Lu Xing , Hong-Ning Dai","doi":"10.1016/j.comnet.2025.111279","DOIUrl":"10.1016/j.comnet.2025.111279","url":null,"abstract":"<div><div>Crowdsourcing leverages distributed mobile devices for task allocation, significantly reducing service costs. However, existing schemes face three major challenges, i.e., data privacy leakage, focusing just on single-attribute tasks, and the inability to accommodate dynamic task updates. To address these issues, we propose a privacy-preserving dynamic multi-attribute task assignment scheme (PDMA). PDMA supports multi-attribute range searches by incorporating spatial, temporal, and keyword constraints. It introduces a hilbert attribute tree (HRAT) for efficient query of multi-attribute tasks and utilizes hilbert R-trees and counting bloom filters (CBF) to facilitate dynamic task updates. To preserve the privacy of spatial and temporal attributes, PDMA integrates the improved symmetric homomorphic encryption (iSHE) scheme, while hash functions preserve the CBF for keyword privacy. Additionally, we propose a secure ternary match protocol (CTP) and a secure subset query scheme (Ssub), which combine iSHE-based ciphertext comparison protocols with simulated ternary content addressable memory (TCAM) to accelerate keyword subset matching. Security and performance analysis demonstrate that PDMA achieves the chosen-query attack security (CQA2-security) and is both practical and efficient.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"265 ","pages":"Article 111279"},"PeriodicalIF":4.4,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850782","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

MFSI: Multi-flow based service identification for encrypted network traffic MFSI：用于加密网络流量的基于多流的服务标识

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-15 DOI: 10.1016/j.comnet.2025.111283

Biying Wang, Baosheng Wang, Ziling Wei, Shuang Zhao, Shuhui Chen, Zhengpeng Li, Minxin Wang

{"title":"MFSI: Multi-flow based service identification for encrypted network traffic","authors":"Biying Wang, Baosheng Wang, Ziling Wei, Shuang Zhao, Shuhui Chen, Zhengpeng Li, Minxin Wang","doi":"10.1016/j.comnet.2025.111283","DOIUrl":"10.1016/j.comnet.2025.111283","url":null,"abstract":"<div><div>Encrypted traffic identification plays a crucial role in improving service quality, optimizing network management, and maintaining network security. Various machine learning and deep learning based methods have been proposed to address the challenge of identifying encrypted traffic. However, existing methods face two main challenges. First, they are easily affected by interfering traffic, which reduces the accuracy of identifying target traffic. Second, they rely on expert annotations to identify unknown applications. In this paper, we propose a multi-flow based method, namely MFSI, for identifying the service of encrypted network traffic. MFSI treats multiple flows as the classification unit to reduce the impact of interfering flows and constructs a robust graph structure Multi-Flow Multi-Relational Graph (MMRG), based on three types of relationships. Then, it introduces Relational Graph Convolutional Networks to update vertex features in MMRG and generates global graph-level representations for multi-flow classification. We conduct experiments on raw network traffic. The results show that MFSI can achieve a classification accuracy of 98.58% without filtering or deleting any traffic, surpassing state-of-the-art schemes. It also performs well in identifying the type of services of unknown encrypted traffic.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"265 ","pages":"Article 111283"},"PeriodicalIF":4.4,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852369","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 survey of attacks on blockchain systems using a layer-based approach 使用基于层的方法对区块链系统进行攻击的调查

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-13 DOI: 10.1016/j.comnet.2025.111274

Joydip Das , Syed Ashraf Al Tasin , Md. Forhad Rabbi , Md. Sadek Ferdous

{"title":"A survey of attacks on blockchain systems using a layer-based approach","authors":"Joydip Das , Syed Ashraf Al Tasin , Md. Forhad Rabbi , Md. Sadek Ferdous","doi":"10.1016/j.comnet.2025.111274","DOIUrl":"10.1016/j.comnet.2025.111274","url":null,"abstract":"<div><div>Blockchain technology is very popular nowadays as it ensures decentralization, transparency, and immutability. However, despite its inherent security features, blockchain-based systems have been frequently targeted by adversaries, raising concerns about their trustworthiness. This paper presents a comprehensive study of 24 major attacks against blockchain systems, categorized in a structured, layer-based approach. The study systematically examines the feasibility, underlying incentives, and underlying vulnerabilities exploited in these attacks. We categorize attacks across four blockchain layers, namely the Network, Consensus, Application, and Meta-Application layers, illustrating the diverse nature of security threats. Furthermore, we propose a systematic analysis that enables an in-depth evaluation of attacks, their interconnections, and cascading effects across different layers. This research intends to contribute to the development of robust security strategies that can mitigate vulnerabilities and increase confidence in decentralized systems by providing a structured technique for analyzing blockchain security concerns. Ultimately, this research underscores the critical need for continuous advancements in blockchain security mechanisms to ensure the resilience of blockchain based systems against emerging and evolving threats.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"265 ","pages":"Article 111274"},"PeriodicalIF":4.4,"publicationDate":"2025-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845204","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

Delay minimization in NTNs: Deployment and caching optimization for satellite- and cache-aided UAV NTNs中的延迟最小化：卫星和缓存辅助无人机的部署和缓存优化

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-13 DOI: 10.1016/j.comnet.2025.111257

Zihao Han , Ting Zhou , Tianheng Xu , Yuling Ouyang , Xianfu Chen , Tao Chen , Honglin Hu

引用次数: 0

Performance enhancement of UAV-enabled MEC systems through intelligent task offloading and resource allocation 通过智能任务卸载和资源分配提高无人机 MEC 系统的性能

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-12 DOI: 10.1016/j.comnet.2025.111280

Mohsen Darchini-Tabrizi , Amirali Pakdaman-Donyavi , Reza Entezari-Maleki , Leonel Sousa

{"title":"Performance enhancement of UAV-enabled MEC systems through intelligent task offloading and resource allocation","authors":"Mohsen Darchini-Tabrizi , Amirali Pakdaman-Donyavi , Reza Entezari-Maleki , Leonel Sousa","doi":"10.1016/j.comnet.2025.111280","DOIUrl":"10.1016/j.comnet.2025.111280","url":null,"abstract":"<div><div>The rapid and continuous growth of the Internet of Things has led to a rising demand for processing and storage solutions that can overcome the limitations of user devices. While cloud computing provides scalability, it often introduces considerable delay. To address this challenge, a computing paradigm that brings resources closer to user devices is preferable. Unmanned Aerial Vehicles (UAVs) have emerged as an effective solution to enhance communication quality and coverage in wireless systems, particularly in specific conditions. This paper presents a UAV-enabled Mobile Edge Computing (MEC) system, where UAVs equipped with computational capabilities provide task offloading services to users. In this system, users process part of their computing tasks locally, while offloading the remaining tasks to UAVs for processing. The primary goal of the proposed algorithm is to minimize processing delays, taking into account the environmental and energy constraints of the UAVs, such as movement boundaries, link blockages, transmission delays, and battery consumption for computation and flight. To achieve this, we propose a Deep Reinforcement Learning algorithm based on the Rainbow Deep Q-Network. This algorithm explores the dynamic and stochastic environment of MEC to deploy an appropriate computation offloading policy. The extensive experiments conducted in this study demonstrate the superior performance of the proposed method. The results show fast convergence to an optimal value and an average improvement of 12.63 percent in delay compared to state-of-the-art methods.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"264 ","pages":"Article 111280"},"PeriodicalIF":4.4,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829125","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

Frequency-domain augmentation and multi-scale feature alignment for improving transferability of adversarial examples 频域增强和多尺度特征对齐提高对抗性示例的可转移性

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-11 DOI: 10.1016/j.comnet.2025.111261

Gui-Hong Li, Heng-Ru Zhang, Fan Min

{"title":"Frequency-domain augmentation and multi-scale feature alignment for improving transferability of adversarial examples","authors":"Gui-Hong Li, Heng-Ru Zhang, Fan Min","doi":"10.1016/j.comnet.2025.111261","DOIUrl":"10.1016/j.comnet.2025.111261","url":null,"abstract":"<div><div>Transfer-based adversarial attack implies that the same adversarial example can fool Deep Neural Networks (DNNs) with different architectures. Model-related approaches train a new surrogate model in local to generate adversarial examples. However, because DNNs with different architectures focus on diverse features within the same data, adversarial examples generated by surrogate models frequently exhibit poor transferability when the surrogate and target models have significant architectural differences. In this paper, we propose a Two-Stage Generation Framework (TSGF) through frequency-domain augmentation and multi-scale feature alignment to address this issue. In the stage of surrogate model training, we enable the surrogate model to capture various features of data through detail and diversity enhancement. Detail enhancement increases the weight of details in clean examples by a frequency-domain augmentation module. Diversity enhancement incorporates slight adversarial examples into the training process to increase the diversity of clean examples. In the stage of adversarial generation, we perturb the distinctive features that different models focus on to improve transferability by a multi-scale feature alignment attack technique. Specifically, we design a loss function using the intermediate multi-layer features of the surrogate model to maximize the difference between the features of clean and adversarial examples. We compare TSGF with a combination of three closely related surrogate model training schemes and the most relevant adversarial attack methods. Results show that TSGF improves transferability across significantly different architectures. The implementation of TSGF is available at <span><span>https://github.com/zhanghrswpu/TSGF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"264 ","pages":"Article 111261"},"PeriodicalIF":4.4,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823463","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

Cache Periscope: Gain insights into the global epidemic of malicious domains through DNS Cache 缓存潜望镜：通过DNS缓存深入了解恶意域的全球流行

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-11 DOI: 10.1016/j.comnet.2025.111245

Yabo Wang , Jiakun Sun , Ruizhi Xiao , Weilong Li , Shuyuan Jin

{"title":"Cache Periscope: Gain insights into the global epidemic of malicious domains through DNS Cache","authors":"Yabo Wang , Jiakun Sun , Ruizhi Xiao , Weilong Li , Shuyuan Jin","doi":"10.1016/j.comnet.2025.111245","DOIUrl":"10.1016/j.comnet.2025.111245","url":null,"abstract":"<div><div>Domain names are often abused for various harmful and illegal activities. To mitigate these threats, security practitioners have proposed detecting malicious domains based on features such as domain name resolution data, semantic attributes, website appearance, and website correlations. Although these techniques have achieved notable results, they remain relatively passive in countering malicious activities. In this paper, we present a large-scale measurement study of the global epidemic of malicious domain names on open resolvers using cache probing techniques. We propose a modified probing method designed for large-scale domain access estimation. Leveraging this method, we examine the access patterns of malicious domains under open resolvers, which are widely deployed and utilized across the Internet, aiming to map the distribution of malicious activities based on the geographic location of open resolvers. Additionally, to the best of our knowledge, we are the first to propose using domain name top lists to estimate the volume of resolver users, which reflects the potential influence of a resolver. The weights of the estimated user volumes are further validated by real DNS traffic. By integrating these two methods, we evaluate the potential impact of malicious domains and conduct extensive measurements and analyses of malicious domain activities on open resolvers worldwide. Our findings reveal the regional distribution of malicious campaigns and provide insights into the global epidemic of malicious domains. Our measurement results demonstrate that practitioners can actively collect threat intelligence using the proposed techniques, gain insights into the current Internet threats, and implement more proactive measures to combat malicious campaigns.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"265 ","pages":"Article 111245"},"PeriodicalIF":4.4,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143860456","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

Real-time latency prediction for cloud gaming applications 云游戏应用的实时延迟预测

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-10 DOI: 10.1016/j.comnet.2025.111235

Doriana Monaco, Alessio Sacco, Daniele Spina, Francesco Strada, Andrea Bottino, Tania Cerquitelli, Guido Marchetto

{"title":"Real-time latency prediction for cloud gaming applications","authors":"Doriana Monaco, Alessio Sacco, Daniele Spina, Francesco Strada, Andrea Bottino, Tania Cerquitelli, Guido Marchetto","doi":"10.1016/j.comnet.2025.111235","DOIUrl":"10.1016/j.comnet.2025.111235","url":null,"abstract":"<div><div>Cloud gaming represents a rapidly growing segment in the entertainment industry, allowing users to stream and interact with high-quality games over the Internet. However, the problem of maintaining a seamless gaming experience is inherent to minimizing user-perceived latency. In this paper, we present CLoud Application lAtency Prediction (CLAAP), a novel solution that, to tolerate challenged network conditions in gaming, predicts such latency via a Machine Learning (ML) model and forecasts future network evolution. The model, trained over diverse network conditions and gaming scenarios, can then update its parameters via a concept drift detection algorithm that suggests a re-training action, reducing the prediction error up to 21% with minimal overhead. We then integrate this network metrics predictor into a game state prediction to further tolerate network latency spikes even from the user perspective, who can continue playing even in adversarial conditions without session interruptions. The results suggest the potential of advanced predictive analytics in mitigating latency issues, thereby setting the stage for more responsive and immersive cloud gaming services.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"264 ","pages":"Article 111235"},"PeriodicalIF":4.4,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829193","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

Security-reliability analysis in uplink cognitive satellite-terrestrial networks with LEO relaying 基于LEO中继的上行认知星地网络安全可靠性分析

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-10 DOI: 10.1016/j.comnet.2025.111272

Peng Zhang , Qing Guo

{"title":"Security-reliability analysis in uplink cognitive satellite-terrestrial networks with LEO relaying","authors":"Peng Zhang , Qing Guo","doi":"10.1016/j.comnet.2025.111272","DOIUrl":"10.1016/j.comnet.2025.111272","url":null,"abstract":"<div><div>This paper investigates the security and reliability performance of hybrid cognitive satellite-terrestrial networks employing a Low Earth Orbit (LEO) satellite as a decode-and-forward (DF) relay. The terrestrial user (TU) operates within an underlay cognitive radio (CR) network, where the primary user (PU) shares its spectrum with the TU while imposing interference power constraints to protect its quality-of-service. To counteract eavesdropping from a terrestrial adversary, the TU incorporates artificial noise (AN) into its transmission, creating a tradeoff between security and reliability. The TU-to-LEO and TU-to-PU links are modeled using Shadowed Rician and Nakagami-<span><math><mi>m</mi></math></span> fading, respectively. Key performance metrics, including the outage probability (OP) and intercept probability (IP), are analyzed under varying system parameters such as power-splitting factor, channel conditions, and interference thresholds. Analytical results are validated through Monte Carlo simulations, and simplified approximations are presented for practical implementation. Results demonstrate the efficacy of the proposed approach in balancing security and reliability.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"264 ","pages":"Article 111272"},"PeriodicalIF":4.4,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817041","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

ST-RDP: A deep spatio-temporal network model for VNF resource demand prediction of Service Function Chains ST-RDP：业务功能链VNF资源需求预测的深度时空网络模型

IF 4.4 2区计算机科学

Computer Networks Pub Date : 2025-04-09 DOI: 10.1016/j.comnet.2025.111260

Junbi Xiao, Qi Wang, Yuhao Zhou

{"title":"ST-RDP: A deep spatio-temporal network model for VNF resource demand prediction of Service Function Chains","authors":"Junbi Xiao, Qi Wang, Yuhao Zhou","doi":"10.1016/j.comnet.2025.111260","DOIUrl":"10.1016/j.comnet.2025.111260","url":null,"abstract":"<div><div>Virtual Network Functions (VNFs) offer comprehensive network services within Service Function Chains (SFCs), aiming to satisfy the diverse performance requirements of various application scenarios. However, the dynamic and unpredictable nature of the network environment poses substantial challenges for resource allocation across VNF instances, potentially leading to resource under-provisioning or over-provisioning. Consequently, accurate prediction of VNF resource demand is critical for enabling dynamic resource adaptation. To address this challenge, we propose a novel deep spatio-temporal network model, referred to as ST-RDP, for resource demand forecasting. Initially, spatial dependencies among VNFs within the same SFC are captured using an modified Adaptive Graph Convolutional Attention (AGCA) module, which effectively models interdependencies between VNFs. Furthermore, the improved Mamba module is employed to extract time-series features, thereby facilitating accurate spatio-temporal forecasting of resource demand. Experimental evaluations on real-world datasets demonstrate that the proposed approach significantly outperforms existing methods in terms of prediction accuracy and effectiveness.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"264 ","pages":"Article 111260"},"PeriodicalIF":4.4,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143820640","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