Computer Networks最新文献

Quantum-resistant ring signature-based authentication scheme against secret key exposure for VANETs

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-17 DOI: 10.1016/j.comnet.2025.111213

Xiaoling Yu , Yuntao Wang , Xin Huang

Vehicular ad-hoc networks (VANETs) can improve traffic management efficiency and driving safety to support the construction of Intelligent Transportation System. Privacy protection in VANETs is one of the challenges that cannot be ignored. To this end, the ring signature is a promising cryptographic primitive for providing privacy protection and authentication. However, in practical ring signature-based VANETs, secret keys of vehicle users used for signing are often exposed because of network attacks or careless use. So far, most predecessors do not guarantee security from secret key exposure. Moreover, many existing ring signature-based systems for VANETs are fragile under quantum computer attacks. In this paper, we construct the first forward secure ring signature scheme from lattices. Based on this scheme, we then design a ring signature-based authentication system for VANETs to guarantee privacy-preserving authentication, message integrity, forward security, and post-quantum security. Our scheme combines the binary tree and lattice basis delegation technique to realize a one-way key update mechanism, where secret keys are ephemeral and updated with generating nodes in the binary tree. Thus, the adversary cannot forge the past signature even if the users’ present secret keys are revealed, which can reduce the damage from key exposure. Furthermore, we give rigorous security proof under the hardness assumption of the underlying Small Integer Solution (SIS) problem in lattice-based cryptography to realize post-quantum security. Finally, we show simulation experiments and comparative analysis to evaluate its performance.

{"title":"Quantum-resistant ring signature-based authentication scheme against secret key exposure for VANETs","authors":"Xiaoling Yu , Yuntao Wang , Xin Huang","doi":"10.1016/j.comnet.2025.111213","DOIUrl":"10.1016/j.comnet.2025.111213","url":null,"abstract":"<div><div>Vehicular ad-hoc networks (VANETs) can improve traffic management efficiency and driving safety to support the construction of Intelligent Transportation System. Privacy protection in VANETs is one of the challenges that cannot be ignored. To this end, the ring signature is a promising cryptographic primitive for providing privacy protection and authentication. However, in practical ring signature-based VANETs, secret keys of vehicle users used for signing are often exposed because of network attacks or careless use. So far, most predecessors do not guarantee security from secret key exposure. Moreover, many existing ring signature-based systems for VANETs are fragile under quantum computer attacks. In this paper, we construct the first forward secure ring signature scheme from lattices. Based on this scheme, we then design a ring signature-based authentication system for VANETs to guarantee privacy-preserving authentication, message integrity, forward security, and post-quantum security. Our scheme combines the binary tree and lattice basis delegation technique to realize a one-way key update mechanism, where secret keys are ephemeral and updated with generating nodes in the binary tree. Thus, the adversary cannot forge the past signature even if the users’ present secret keys are revealed, which can reduce the damage from key exposure. Furthermore, we give rigorous security proof under the hardness assumption of the underlying Small Integer Solution (SIS) problem in lattice-based cryptography to realize post-quantum security. Finally, we show simulation experiments and comparative analysis to evaluate its performance.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111213"},"PeriodicalIF":4.4,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642189","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

Machine learning approaches for active queue management: A survey, taxonomy, and future directions

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-17 DOI: 10.1016/j.comnet.2025.111174

Mohammad Parsa Toopchinezhad, Mahmood Ahmadi

Active Queue Management (AQM), a network-layer congestion control technique endorsed by the Internet Engineering Task Force (IETF), encourages routers to discard packets before the occurrence of buffer overflow. Traditional AQM techniques often employ heuristic approaches that require meticulous parameter adjustments, limiting their real-world applicability. In contrast, Machine Learning (ML) approaches offer highly adaptive, data-driven solutions custom to dynamic network conditions. Consequently, many researchers have adapted ML for AQM throughout the years, resulting in a wide variety of algorithms ranging from predicting congestion via supervised learning to discovering optimal packet-dropping policies with reinforcement learning. Despite these remarkable advancements, no previous work has compiled these methods in the form of a survey article. This paper presents the first thorough documentation and analysis of ML-based algorithms for AQM, in which the strengths and limitations of each proposed method are evaluated and compared. In addition, a novel taxonomy of ML approaches based on methodology is also established. The review is concluded by discussing unexplored research gaps and potential new directions for more robust ML-AQM methods.

主动队列管理（AQM）是互联网工程任务组（IETF）认可的一种网络层拥塞控制技术，它鼓励路由器在缓冲区溢出之前丢弃数据包。传统的 AQM 技术通常采用启发式方法，需要对参数进行细致的调整，从而限制了其在现实世界中的适用性。相比之下，机器学习（ML）方法可根据动态网络条件提供高度自适应、数据驱动的解决方案。因此，多年来，许多研究人员将 ML 用于 AQM，从而产生了各种各样的算法，从通过监督学习预测拥塞情况，到通过强化学习发现最佳丢包策略，不一而足。尽管取得了这些令人瞩目的进步，但以前的工作还没有以调查文章的形式对这些方法进行汇编。本文首次对基于 ML 的 AQM 算法进行了详尽的记录和分析，对每种建议方法的优势和局限性进行了评估和比较。此外，还根据方法论建立了新的 ML 方法分类法。综述的最后讨论了尚未探索的研究空白和潜在的新方向，以获得更强大的 ML-AQM 方法。

{"title":"Machine learning approaches for active queue management: A survey, taxonomy, and future directions","authors":"Mohammad Parsa Toopchinezhad, Mahmood Ahmadi","doi":"10.1016/j.comnet.2025.111174","DOIUrl":"10.1016/j.comnet.2025.111174","url":null,"abstract":"<div><div>Active Queue Management (AQM), a network-layer congestion control technique endorsed by the Internet Engineering Task Force (IETF), encourages routers to discard packets before the occurrence of buffer overflow. Traditional AQM techniques often employ heuristic approaches that require meticulous parameter adjustments, limiting their real-world applicability. In contrast, Machine Learning (ML) approaches offer highly adaptive, data-driven solutions custom to dynamic network conditions. Consequently, many researchers have adapted ML for AQM throughout the years, resulting in a wide variety of algorithms ranging from predicting congestion via supervised learning to discovering optimal packet-dropping policies with reinforcement learning. Despite these remarkable advancements, no previous work has compiled these methods in the form of a survey article. This paper presents the first thorough documentation and analysis of ML-based algorithms for AQM, in which the strengths and limitations of each proposed method are evaluated and compared. In addition, a novel taxonomy of ML approaches based on methodology is also established. The review is concluded by discussing unexplored research gaps and potential new directions for more robust ML-AQM methods.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111174"},"PeriodicalIF":4.4,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643851","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

Collision avoidance by mitigating uncertain packet loss in multi-hop wireless IoT networks

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-17 DOI: 10.1016/j.comnet.2025.111205

Woo-Hyeok Jang, Seung-Jae Han

Multi-hop wireless relaying is an effective solution to provide connectivity to IoT devices in places that are difficult to reach. Spatial reuse for higher spectral efficiency by allowing simultaneous transmissions, however, causes self-interference unless transmissions are carefully coordinated. To solve this issue, recently, ML(Machine Learning)-based transmission scheduling has been explored in many literatures. Existing ML-based schemes, however, have limitation in that they do not account for the control overhead associated with schedule deployment and network state collection. In this paper, we propose a DRL (Deep Reinforcement Learning)-based TDMA scheduling scheme that aims to optimize network throughput and minimize energy consumption while avoiding collisions. More specifically, we use a Sequence-to-Sequence (S2S) neural network to compose the DRL policy. One of the key novelties of our scheme is that the schedule deployment is conducted sparsely to reduce the control overhead. This causes uncertainties due to the random packet losses, and we mitigate the uncertainties via a technique called redundant scheduling. Simulation results demonstrate that the proposed scheme is scalable and converges quickly, and it outperforms existing schemes under various network conditions.

{"title":"Collision avoidance by mitigating uncertain packet loss in multi-hop wireless IoT networks","authors":"Woo-Hyeok Jang, Seung-Jae Han","doi":"10.1016/j.comnet.2025.111205","DOIUrl":"10.1016/j.comnet.2025.111205","url":null,"abstract":"<div><div>Multi-hop wireless relaying is an effective solution to provide connectivity to IoT devices in places that are difficult to reach. Spatial reuse for higher spectral efficiency by allowing simultaneous transmissions, however, causes self-interference unless transmissions are carefully coordinated. To solve this issue, recently, ML(Machine Learning)-based transmission scheduling has been explored in many literatures. Existing ML-based schemes, however, have limitation in that they do not account for the control overhead associated with schedule deployment and network state collection. In this paper, we propose a DRL (Deep Reinforcement Learning)-based TDMA scheduling scheme that aims to optimize network throughput and minimize energy consumption while avoiding collisions. More specifically, we use a Sequence-to-Sequence (S2S) neural network to compose the DRL policy. One of the key novelties of our scheme is that the schedule deployment is conducted sparsely to reduce the control overhead. This causes uncertainties due to the random packet losses, and we mitigate the uncertainties via a technique called redundant scheduling. Simulation results demonstrate that the proposed scheme is scalable and converges quickly, and it outperforms existing schemes under various network conditions.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111205"},"PeriodicalIF":4.4,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642190","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 and future outlook on indoor location fingerprinting privacy preservation

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-15 DOI: 10.1016/j.comnet.2025.111199

Amir Fathalizadeh , Vahideh Moghtadaiee , Mina Alishahi

The pervasive integration of Indoor Positioning Systems (IPS) arises from the limitations of Global Navigation Satellite Systems (GNSS) in indoor environments, leading to the widespread adoption of Location-Based Services (LBS) in places such as shopping malls, airports, hospitals, museums, corporate campuses, and smart buildings. Specifically, indoor location fingerprinting (ILF) systems employ diverse signal fingerprints from user devices, enabling precise location identification by Location Service Providers (LSP). Despite its broad applications across various domains, ILF introduces a notable privacy risk, as both LSP and potential adversaries inherently have access to this sensitive information, compromising users’ privacy. Consequently, concerns regarding privacy vulnerabilities in this context necessitate a focused exploration of privacy-preserving mechanisms. In response to these concerns, this survey presents a comprehensive review of Indoor Location Fingerprinting Privacy-Preserving Mechanisms (ILFPPM) based on cryptographic, anonymization, differential privacy (DP), and federated learning (FL) techniques. We also propose a distinctive and novel grouping of privacy vulnerabilities, adversary models, privacy attacks, and evaluation metrics specific to ILF systems. Given the identified limitations and research gaps in this survey, we highlight numerous prospective opportunities for future investigation, aiming to motivate researchers interested in advancing ILF systems. This survey constitutes a valuable reference for researchers and provides a clear overview for those beyond this specific research domain. To further help the researchers, we have created an online resource repository, which can be found at https://github.com/amir-ftlz/ilfppm.

{"title":"A survey and future outlook on indoor location fingerprinting privacy preservation","authors":"Amir Fathalizadeh , Vahideh Moghtadaiee , Mina Alishahi","doi":"10.1016/j.comnet.2025.111199","DOIUrl":"10.1016/j.comnet.2025.111199","url":null,"abstract":"<div><div>The pervasive integration of Indoor Positioning Systems (IPS) arises from the limitations of Global Navigation Satellite Systems (GNSS) in indoor environments, leading to the widespread adoption of Location-Based Services (LBS) in places such as shopping malls, airports, hospitals, museums, corporate campuses, and smart buildings. Specifically, indoor location fingerprinting (ILF) systems employ diverse signal fingerprints from user devices, enabling precise location identification by Location Service Providers (LSP). Despite its broad applications across various domains, ILF introduces a notable privacy risk, as both LSP and potential adversaries inherently have access to this sensitive information, compromising users’ privacy. Consequently, concerns regarding privacy vulnerabilities in this context necessitate a focused exploration of privacy-preserving mechanisms. In response to these concerns, this survey presents a comprehensive review of Indoor Location Fingerprinting Privacy-Preserving Mechanisms (ILFPPM) based on cryptographic, anonymization, differential privacy (DP), and federated learning (FL) techniques. We also propose a distinctive and novel grouping of privacy vulnerabilities, adversary models, privacy attacks, and evaluation metrics specific to ILF systems. Given the identified limitations and research gaps in this survey, we highlight numerous prospective opportunities for future investigation, aiming to motivate researchers interested in advancing ILF systems. This survey constitutes a valuable reference for researchers and provides a clear overview for those beyond this specific research domain. To further help the researchers, we have created an online resource repository, which can be found at <span><span>https://github.com/amir-ftlz/ilfppm</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111199"},"PeriodicalIF":4.4,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636503","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

Enhancing IoT security: A competitive coevolutionary strategy for detecting RPL attacks in challenging attack environments

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-13 DOI: 10.1016/j.comnet.2025.111185

Selim Yılmaz

Internet of Things (IoT) is a recent technology that allows heterogeneous devices to communicate with each other and the Internet. Designed specifically for IoT-enabled networks, the IPv6 Routing Protocol for Low Power Lossy Network (RPL) is adopted as standard routing protocol today. While RPL facilitates efficient routing between IoT devices, it is very susceptible to attacks, leading to numerous threats targeting different aspects of the nodes and network. Consequently, several efforts have been made to develop intrusion detection systems to secure RPL-operated networks. However, many existing solutions are tailored to specific attacks, making them unsuitable for other RPL attacks. Additionally, they depend on fixed simulations with specific scenarios, neglecting the influence of attack environments on detection system performance. The impact of RPL attacks varies with factors such as attacker density and position in the network. Consequently, it is crucial to design IDS that can effectively handle these dynamic conditions. This study addresses these challenges by proposing a competitive coevolution-based intrusion detection system that focuses on the most challenging attack environments. To achieve this, the intrusion detection algorithm and challenging attack environments are competitively evolved. Targeting the network’s topology, traffic, and resources through the exploitation of control packets, this study investigates 11 RPL attacks: blackhole, DIS flooding, DAG inconsistency, DAO inconsistency, decreased rank, energy depletion, forwarding misbehavior, increased version, spam DIS, selective forwarding, and worst parent. To assess detection performance, a wide range of evaluation metrics such as accuracy, precision, recall, false alarm rate, and F1-score are used. The findings demonstrate that the proposed system ensures strong detection performance with very low memory and power consumption, suggesting its effectiveness against the attacks threatening the multiple aspects of the network and its applicability on resource-constrained nodes.

{"title":"Enhancing IoT security: A competitive coevolutionary strategy for detecting RPL attacks in challenging attack environments","authors":"Selim Yılmaz","doi":"10.1016/j.comnet.2025.111185","DOIUrl":"10.1016/j.comnet.2025.111185","url":null,"abstract":"<div><div>Internet of Things (IoT) is a recent technology that allows heterogeneous devices to communicate with each other and the Internet. Designed specifically for IoT-enabled networks, the IPv6 Routing Protocol for Low Power Lossy Network (RPL) is adopted as standard routing protocol today. While RPL facilitates efficient routing between IoT devices, it is very susceptible to attacks, leading to numerous threats targeting different aspects of the nodes and network. Consequently, several efforts have been made to develop intrusion detection systems to secure RPL-operated networks. However, many existing solutions are tailored to specific attacks, making them unsuitable for other RPL attacks. Additionally, they depend on fixed simulations with specific scenarios, neglecting the influence of attack environments on detection system performance. The impact of RPL attacks varies with factors such as attacker density and position in the network. Consequently, it is crucial to design IDS that can effectively handle these dynamic conditions. This study addresses these challenges by proposing a competitive coevolution-based intrusion detection system that focuses on the most challenging attack environments. To achieve this, the intrusion detection algorithm and challenging attack environments are competitively evolved. Targeting the network’s topology, traffic, and resources through the exploitation of control packets, this study investigates 11 RPL attacks: blackhole, DIS flooding, DAG inconsistency, DAO inconsistency, decreased rank, energy depletion, forwarding misbehavior, increased version, spam DIS, selective forwarding, and worst parent. To assess detection performance, a wide range of evaluation metrics such as accuracy, precision, recall, false alarm rate, and F1-score are used. The findings demonstrate that the proposed system ensures strong detection performance with very low memory and power consumption, suggesting its effectiveness against the attacks threatening the multiple aspects of the network and its applicability on resource-constrained nodes.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111185"},"PeriodicalIF":4.4,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636498","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 review on intrusion detection datasets: tools, processes, and features

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-13 DOI: 10.1016/j.comnet.2025.111177

Daniela Pinto , Ivone Amorim , Eva Maia , Isabel Praça

Network intrusion detection systems are fundamental to the early detection of anomalous behaviour in networks. Modern versions of these tools take advantage of Machine Learning to process large amounts of data, identify patterns, and make predictions. Their development relies on the ability to access good historical network data. Therefore, the research community has been actively working on creating new datasets, and network traffic analysis tools are frequently used in this context. This study provides a comprehensive review of existing tools for network traffic analysis, highlighting their main advantages and drawbacks. A categorisation for these tools is introduced, as well as an overview of the dataset creation process by combining one or more of these categories. An updated analysis of existing datasets is also provided, along with details regarding their creation, highlighting the progression in dataset production. Finally, the impact of dataset features is discussed, underscoring their role in enhancing the effectiveness of network intrusion detection systems.

引用次数: 0

P-HotStuff: Parallel BFT algorithm with throughput insensitive to propagation delay

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-12 DOI: 10.1016/j.comnet.2025.111183

Fei Zhu, Lin You, Jixiang Wang, Lei Li

In this work, we present P-HotStuff, a novel variant of HotStuff consensus algorithm with multiple parallel operations, which can effectively solve the bottleneck of the Byzantine Fault Tolerance (BFT) algorithms that employ the leader-based consensus model, where the throughput is sensitive to Propagation Delay, resulting in the bandwidth of each node is frequently idle. The parallel operations consist of three parts. First, the Broadcast layer is decoupled from the Agreement layer and they run in parallel, where the Broadcast is for preparing the inputs for each consensus, and the Agreement is for determining the inputs. Secondly, instead of only the leader, all the nodes can prepare the inputs in parallel. Lastly, the node can prepare each input in parallel, which means that it can directly prepare its next input without waiting for the completion of its preceding preparation. We have conducted the experiments and compared our P-HotStuff with HotStuff and the latest work Motorway. The experimental results show that P-HotStuff can achieve an average throughput that is about 20 times that of HotStuff and 50% higher than that of Motorway under the condition of about 60 nodes, 256 Bytes payload, batch size of 400 and 100 Mbps bandwidth in a Wide Area Network spanning multiple states with an average propagation delay of 260 ms.

{"title":"P-HotStuff: Parallel BFT algorithm with throughput insensitive to propagation delay","authors":"Fei Zhu, Lin You, Jixiang Wang, Lei Li","doi":"10.1016/j.comnet.2025.111183","DOIUrl":"10.1016/j.comnet.2025.111183","url":null,"abstract":"<div><div>In this work, we present P-HotStuff, a novel variant of HotStuff consensus algorithm with multiple parallel operations, which can effectively solve the bottleneck of the Byzantine Fault Tolerance (BFT) algorithms that employ the leader-based consensus model, where the throughput is sensitive to Propagation Delay, resulting in the bandwidth of each node is frequently idle. The parallel operations consist of three parts. First, the <strong>Broadcast</strong> layer is decoupled from the <strong>Agreement</strong> layer and they run in parallel, where the <strong>Broadcast</strong> is for preparing the inputs for each consensus, and the <strong>Agreement</strong> is for determining the inputs. Secondly, instead of only the leader, all the nodes can prepare the inputs in parallel. Lastly, the node can prepare each input in parallel, which means that it can directly prepare its next input without waiting for the completion of its preceding preparation. We have conducted the experiments and compared our P-HotStuff with HotStuff and the latest work Motorway. The experimental results show that P-HotStuff can achieve an average throughput that is about 20 times that of HotStuff and 50% higher than that of Motorway under the condition of about 60 nodes, 256 Bytes payload, batch size of 400 and 100 Mbps bandwidth in a Wide Area Network spanning multiple states with an average propagation delay of 260 ms.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111183"},"PeriodicalIF":4.4,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143642187","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

ArchW3: An adaptive blockchain wallet architecture for Web3 applications

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-11 DOI: 10.1016/j.comnet.2025.111182

E.M. Cruz , J.R.D.S. Júnior , Y.H.J. Souza , G.L.S.S. Jesus , M.L.M. Peixoto

The evolution of Web3 technologies presents significant challenges in integrating decentralized systems with Web2 infrastructures, particularly in secure digital asset management and blockchain interoperability. Existing digital wallet solutions struggle to ensure seamless interoperability, robust key management, and effective integration with both public and private blockchain networks, all while meeting the growing demand for flexible and user-friendly solutions in this rapidly expanding market. To tackle these issues, this paper introduces ArchW3, a modular framework designed to address these challenges through three core components: a Custody Service for secure key management, a Provider Service ensuring blockchain network interoperability, and a Web2/Web3 Communication Interface to simplify application development. Experimental validation involved a

2^{k}

factorial design, analyzing transaction processing time, memory usage, CPU usage, and energy consumption under diverse configurations. Results demonstrated ArchW3’s adaptability across EVM and non-EVM networks, such as Ganache and Solana, respectively. Solana exhibited superior efficiency, achieving up to 85% in memory and energy performance under high transactional loads, while EVM-Ganache excelled in low-load processing scenarios with up to 40% better performance. The ArchW3 framework was successfully deployed at Bank BV in Brazil, showcasing its applicability in real financial environments by integrating banking services with Web3 infrastructure.

Web3 技术的发展给去中心化系统与 Web2 基础设施的集成带来了巨大挑战，特别是在安全数字资产管理和区块链互操作性方面。现有的数字钱包解决方案难以确保无缝互操作性、稳健的密钥管理以及与公共和私有区块链网络的有效集成，同时也难以满足这一快速发展的市场对灵活、用户友好的解决方案日益增长的需求。为了解决这些问题，本文介绍了ArchW3，这是一个模块化框架，旨在通过三个核心组件应对这些挑战：用于安全密钥管理的保管服务（Custody Service）、确保区块链网络互操作性的提供商服务（Provider Service）以及简化应用程序开发的Web2/Web3通信接口。实验验证采用了 2k 因式设计，分析了不同配置下的交易处理时间、内存使用率、CPU 使用率和能耗。结果表明，ArchW3 能够适应 EVM 和非 EVM 网络，如 Ganache 和 Solana。Solana 表现出卓越的效率，在高事务负载下实现了高达 85% 的内存和能耗性能，而 EVM-Ganache 则在低负载处理场景中表现出色，性能提高了 40%。ArchW3 框架已在巴西 BV 银行成功部署，通过将银行服务与 Web3 基础设施集成，展示了其在实际金融环境中的适用性。

{"title":"ArchW3: An adaptive blockchain wallet architecture for Web3 applications","authors":"E.M. Cruz , J.R.D.S. Júnior , Y.H.J. Souza , G.L.S.S. Jesus , M.L.M. Peixoto","doi":"10.1016/j.comnet.2025.111182","DOIUrl":"10.1016/j.comnet.2025.111182","url":null,"abstract":"<div><div>The evolution of Web3 technologies presents significant challenges in integrating decentralized systems with Web2 infrastructures, particularly in secure digital asset management and blockchain interoperability. Existing digital wallet solutions struggle to ensure seamless interoperability, robust key management, and effective integration with both public and private blockchain networks, all while meeting the growing demand for flexible and user-friendly solutions in this rapidly expanding market. To tackle these issues, this paper introduces ArchW3, a modular framework designed to address these challenges through three core components: a Custody Service for secure key management, a Provider Service ensuring blockchain network interoperability, and a Web2/Web3 Communication Interface to simplify application development. Experimental validation involved a <span><math><msup><mrow><mn>2</mn></mrow><mrow><mi>k</mi></mrow></msup></math></span> factorial design, analyzing <em>transaction processing time</em>, <em>memory usage</em>, <em>CPU usage</em>, and <em>energy consumption under diverse configurations</em>. Results demonstrated ArchW3’s adaptability across EVM and non-EVM networks, such as Ganache and Solana, respectively. Solana exhibited superior efficiency, achieving up to 85% in memory and energy performance under high transactional loads, while EVM-Ganache excelled in low-load processing scenarios with up to 40% better performance. The ArchW3 framework was successfully deployed at Bank BV in Brazil, showcasing its applicability in real financial environments by integrating banking services with Web3 infrastructure.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111182"},"PeriodicalIF":4.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143636497","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

Deep Reinforcement Learning and SQP-driven task offloading decisions in vehicular edge computing networks

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-11 DOI: 10.1016/j.comnet.2025.111180

Ehzaz Mustafa , Junaid Shuja , Faisal Rehman , Abdallah Namoun , Muhammad Bilal , Kashif Bilal

Vehicular Edge Computing offers low latency and reduced energy consumption for innovative applications through computation offloading in vehicular networks. However, making optimal offloading decisions and resource allocation remains challenging due to varying speeds, locations, channel quality constraints, and characteristics of both vehicles and tasks. To address these challenges, we propose a three-layered architecture and introduce a two-level algorithm named Sequential Quadratic Programming-based Dueling Double Deep Q Networks (SQ-DDTO) for optimal offloading actions and resource allocation. The joint computation offloading decision and resource allocation is a mixed integer nonlinear programming problem. To solve it, we first decouple the computation offloading decision sub-problem from resource allocation and address it using Dueling DDQN, which incorporates separate state values and action advantages. This decomposition allows for more granular control of computation tasks, leading to significantly better results. To enhance sample efficiency and learning in such complex networks, we employ Prioritized Experience Replay (PER). By prioritizing experiences based on their importance, PER enhances learning efficiency, allowing the agent to adapt quickly to changing conditions and optimize task offloading decisions in real time. Following this decomposition, we use Sequential Quadratic Programming (SQP) to solve for optimal resource allocation. SQP is chosen due to its effectiveness in handling non-convexity and complex constraints. Moreover, it has strong local convergence properties and utilizes gradient information which is crucial where rapid decision-making is necessary. Experimental results demonstrate the effectiveness of the proposed algorithm in terms of average delay, energy consumption, and task loss rate. For example. the proposed algorithm reduces the system cost by 25.1% compared to DQN and 16.67% compared to both DDQN and DDPG. Similarly. our method reduces the task loss rate by 37.06% compared to DQN, 34.78% compared to DDPG and 10.2% compared to DDQN.

{"title":"Deep Reinforcement Learning and SQP-driven task offloading decisions in vehicular edge computing networks","authors":"Ehzaz Mustafa , Junaid Shuja , Faisal Rehman , Abdallah Namoun , Muhammad Bilal , Kashif Bilal","doi":"10.1016/j.comnet.2025.111180","DOIUrl":"10.1016/j.comnet.2025.111180","url":null,"abstract":"<div><div>Vehicular Edge Computing offers low latency and reduced energy consumption for innovative applications through computation offloading in vehicular networks. However, making optimal offloading decisions and resource allocation remains challenging due to varying speeds, locations, channel quality constraints, and characteristics of both vehicles and tasks. To address these challenges, we propose a three-layered architecture and introduce a two-level algorithm named Sequential Quadratic Programming-based Dueling Double Deep Q Networks (SQ-DDTO) for optimal offloading actions and resource allocation. The joint computation offloading decision and resource allocation is a mixed integer nonlinear programming problem. To solve it, we first decouple the computation offloading decision sub-problem from resource allocation and address it using Dueling DDQN, which incorporates separate state values and action advantages. This decomposition allows for more granular control of computation tasks, leading to significantly better results. To enhance sample efficiency and learning in such complex networks, we employ Prioritized Experience Replay (PER). By prioritizing experiences based on their importance, PER enhances learning efficiency, allowing the agent to adapt quickly to changing conditions and optimize task offloading decisions in real time. Following this decomposition, we use Sequential Quadratic Programming (SQP) to solve for optimal resource allocation. SQP is chosen due to its effectiveness in handling non-convexity and complex constraints. Moreover, it has strong local convergence properties and utilizes gradient information which is crucial where rapid decision-making is necessary. Experimental results demonstrate the effectiveness of the proposed algorithm in terms of average delay, energy consumption, and task loss rate. For example. the proposed algorithm reduces the system cost by 25.1% compared to DQN and 16.67% compared to both DDQN and DDPG. Similarly. our method reduces the task loss rate by 37.06% compared to DQN, 34.78% compared to DDPG and 10.2% compared to DDQN.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111180"},"PeriodicalIF":4.4,"publicationDate":"2025-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143620578","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

SK-CFR: Rerouting critical flows through discrete soft actor–critic within the KP-GNN framework

IF 4.4 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computer Networks

Pub Date : 2025-03-10 DOI: 10.1016/j.comnet.2025.111175

Lianming Zhang, Shuqiang Peng, Pingping Dong

Intelligent routing methodologies often necessitate the rerouting of a significant portion of traffic, leading to superfluous overhead and erratic network performance marked by heightened End-to-End (E2E) latency. A promising approach involves harnessing reinforcement learning to pinpoint and redirect traffic that exerts a substantial impact on network performance. To minimize overhead and achieve optimal latency, we introduce an innovative routing solution, SK-CFR — founded on Discrete Soft Actor–Critic and

K

-hop message Passing Graph Neural Network (KP-GNN) for Critical Flow Rerouting — that is rooted in this strategic framework. This solution integrates bounding subgraphs within the KP-GNN framework, enabling enhanced feature extraction via an expanded dimensionality in the graph’s structure. Furthermore, to seamlessly adapt to the discrete action space, we have refined and deployed the Discrete Soft Actor–Critic (DSAC) algorithm, guaranteeing a more efficient exploration of critical flows by leveraging entropy regularization throughout the training phase. Our solution has undergone rigorous simulation across four real-world network topologies, yielding a remarkable 12% reduction in network latency compared to state-of-the-art Critical Flow Rerouting-Reinforcement Learning (CFR-RL) methods, while demonstrating robust resilience against dynamic network changes.

{"title":"SK-CFR: Rerouting critical flows through discrete soft actor–critic within the KP-GNN framework","authors":"Lianming Zhang, Shuqiang Peng, Pingping Dong","doi":"10.1016/j.comnet.2025.111175","DOIUrl":"10.1016/j.comnet.2025.111175","url":null,"abstract":"<div><div>Intelligent routing methodologies often necessitate the rerouting of a significant portion of traffic, leading to superfluous overhead and erratic network performance marked by heightened End-to-End (E2E) latency. A promising approach involves harnessing reinforcement learning to pinpoint and redirect traffic that exerts a substantial impact on network performance. To minimize overhead and achieve optimal latency, we introduce an innovative routing solution, SK-CFR — founded on Discrete Soft Actor–Critic and <span><math><mi>K</mi></math></span>-hop message Passing Graph Neural Network (KP-GNN) for Critical Flow Rerouting — that is rooted in this strategic framework. This solution integrates bounding subgraphs within the KP-GNN framework, enabling enhanced feature extraction via an expanded dimensionality in the graph’s structure. Furthermore, to seamlessly adapt to the discrete action space, we have refined and deployed the Discrete Soft Actor–Critic (DSAC) algorithm, guaranteeing a more efficient exploration of critical flows by leveraging entropy regularization throughout the training phase. Our solution has undergone rigorous simulation across four real-world network topologies, yielding a remarkable 12% reduction in network latency compared to state-of-the-art Critical Flow Rerouting-Reinforcement Learning (CFR-RL) methods, while demonstrating robust resilience against dynamic network changes.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"262 ","pages":"Article 111175"},"PeriodicalIF":4.4,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643850","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