Computer Networks最新文献

{"title":"Mobility-Aware Predictive Split Federated Learning for 6G vehicular networks with ultra-low latency guarantees","authors":"Iftikhar Rasheed ,&nbsp;Hala Mostafa","doi":"10.1016/j.comnet.2025.111553","DOIUrl":"10.1016/j.comnet.2025.111553","url":null,"abstract":"<div><div>The integration of distributed learning in 6G vehicular networks faces significant challenges due to high mobility, stringent latency requirements, and resource constraints at the network edge. This paper proposes MAPSFL, a novel mobility-aware predictive split federated learning framework that seamlessly integrates mobility prediction, dynamic model splitting, and hierarchical learning architectures to enable efficient distributed learning in highly mobile vehicular environments. Our framework employs a predictive mobility model to optimize resource allocation and model splitting decisions while maintaining ultra-low latency guarantees through adaptive compression and selective parameter transmission mechanisms. Theoretical analysis provides convergence guarantees under dynamic network conditions, while extensive experimental results demonstrate that MAPSFL achieves 31% reduction in CPU utilization, 28% lower bandwidth consumption, and 34% reduction in end-to-end training latency compared to state-of-the-art approaches. The proposed work achieved 85% efficiency at large scales of vehicles, i.e. 5000, while ensuring the required latency of 100ms, thus making it particularly suitable for safety-critical vehicular applications. The comprehensive evaluation of the proposed method validates its effectiveness in addressing the challenges of high mobility, resource constraints, and network dynamics in 6G vehicular networks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111553"},"PeriodicalIF":4.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704134","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}

{"title":"STAR-RIS-assisted UAV-enabled MEC network: Minimizing long-term latency and system stability optimization","authors":"Yaoping Zeng,&nbsp;Shisen Chen,&nbsp;Yimeng Ge","doi":"10.1016/j.comnet.2025.111563","DOIUrl":"10.1016/j.comnet.2025.111563","url":null,"abstract":"<div><div>Unmanned aerial vehicle (UAV)-assisted wireless power transfer (WPT) is a promising technology for delivering sustainable energy to energy-constrained ground users (GUs) in mobile edge computing (MEC) networks. Nevertheless, the network performance is severely limited by channel fading. Compared with the conventional reconfigurable intelligent surface (RIS) limited to half-space coverage, the simultaneously transmitting and reflecting (STAR)-RIS achieves full-space coverage, thereby enhancing both WPT efficiency and computational task offloading performance. To fully investigate the potential of STAR-RIS, this paper proposes a STAR-RIS-assisted UAV-enabled MEC system aiming to minimize long-term latency while ensuring system stability by jointly optimizing time slot allocation, STAR-RIS coefficient matrices, and UAV trajectory. By leveraging the Lyapunov optimization method, the original long-term stochastic optimization problem is transformed into tractable deterministic sub-problems, which are then solved by using successive convex approximation, penalty functions, and convex optimization techniques. Simulation results demonstrate that the proposed scheme effectively balances long-term latency reduction and system stability, achieving significant performance gains compared with baseline schemes.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111563"},"PeriodicalIF":4.4,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144711244","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}

{"title":"Betastack: Enhancing base station traffic prediction with network-specific Large Language Models","authors":"Quanfeng Lv ,&nbsp;Yuan Chang ,&nbsp;Tong Li ,&nbsp;Jingguo Ge","doi":"10.1016/j.comnet.2025.111557","DOIUrl":"10.1016/j.comnet.2025.111557","url":null,"abstract":"<div><div>Accurate traffic forecasting in base station networks is crucial for efficient network management, resource allocation, and ensuring quality of service. This paper introduces BetaStack, a novel network-specific Large Language Model (LLM) designed to enhance base station traffic prediction. Unlike existing approaches, BetaStack incorporates physical constraints and a specialized network protocol embedding layer that captures the hierarchical structure of network traffic data. Through fine-tuning with these network-specific adaptations and a self-regressive prediction mechanism, BetaStack effectively leverages the powerful sequence modeling capabilities of LLMs to address the intricacies of network traffic. Extensive experiments on real-world data from base station cells in Guangdong, China demonstrate that BetaStack achieves significant performance improvements over both state-of-the-art time-series forecasting models and specialized network traffic prediction models. These results underscore the potential of BetaStack to improve the accuracy of network traffic prediction, enabling more efficient network management. The code can be found in <span><span>https://github.com/lqf0624/BetaStack.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111557"},"PeriodicalIF":4.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686301","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}

{"title":"Energy-efficient and reliable data collection in receiver-initiated wake-up radio enabled IoT networks","authors":"Syed Luqman Shah ,&nbsp;Ziaul Haq Abbas ,&nbsp;Ghulam Abbas ,&nbsp;Nurul Huda Mahmood","doi":"10.1016/j.comnet.2025.111548","DOIUrl":"10.1016/j.comnet.2025.111548","url":null,"abstract":"<div><div>In unmanned aerial vehicle (UAV)-assisted wake-up radio (WuR)-enabled internet of things (IoT) networks, UAVs can instantly activate the main radios (MRs) of the sensor nodes (SNs) with a wake-up call (WuC) for efficient data collection in mission-driven data collection scenarios. However, the spontaneous response of numerous SNs to the UAV’s WuC can lead to significant packet loss and collisions, as WuR does not exhibit its superiority for high-traffic loads. To address this challenge, we propose an innovative receiver-initiated WuR UAV-assisted clustering (RI-WuR-UAC) medium access control (MAC) protocol to achieve low latency and high reliability in ultra-low power consumption applications. We model the proposed protocol using the <span><math><mrow><mi>M</mi><mo>/</mo><mi>G</mi><mo>/</mo><mn>1</mn><mo>/</mo><mn>2</mn></mrow></math></span> queuing framework and derive expressions for key performance metrics, i.e., channel busyness probability, probability of successful clustering, average SN energy consumption, and average transmission delay. The RI-WuR-UAC protocol employs three distinct data flow models, tailored to different network traffic scenarios, which perform three different MAC mechanisms: channel assessment (CCA) clustering for light traffic loads, backoff plus CCA clustering for dense and heavy traffic, and adaptive clustering for variable traffic loads. Simulation results demonstrate that the RI-WuR-UAC protocol significantly outperforms the benchmark sub-carrier modulation clustering protocol. By varying the network load, we capture the trade-offs among the performance metrics, showcasing the superior efficiency and reliability of the RI-WuR-UAC protocol.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111548"},"PeriodicalIF":4.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144696465","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}

{"title":"Permissioned blockchain architecture enabling bounded-time PBFT consensus over deterministic networks","authors":"Wenwei Huang ,&nbsp;Tianyu Kang ,&nbsp;Li Guo ,&nbsp;Luo Deng","doi":"10.1016/j.comnet.2025.111547","DOIUrl":"10.1016/j.comnet.2025.111547","url":null,"abstract":"<div><div>With the advent of next-generation network, the demand for time-sensitive services in fields such as the IoT the IoD has been increasing. Meanwhile, integrating blockchain technology is becoming increasingly meaningful in IoT scenario due to its enhanced security, transparency and fault tolerance. At this point, to enable blockchain systems to provide time-sensitive services in scenarios such as IIoT, this study proposes an permissioned blockchain architecture based on deterministic network aimed at reaching PBFT consensus in bounded time, referred to as confidence duration (CD). However, congestion can compromise the validity of the CD. To address this, we leverage the PBFT consensus model. This model demonstrates the architecture’s effectiveness by breaking down the consensus process into a series of finite, bounded-latency transmissions, thereby allowing for the calculation of the CD even under potential network congestion. Then, based on this model, this paper proposes a STA scheduling mechanism to address the congestion problem in the PBFT consensus. Finally, our simulations found that the architecture is effective, the computation of CD is correct and the STA scheduling mechanism can effectively address congestion to ensure functionality of CD.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111547"},"PeriodicalIF":4.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144686297","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}

{"title":"A modular system for real-time intrusion detection on local area networks","authors":"Ilhan Firat Kilincer","doi":"10.1016/j.comnet.2025.111577","DOIUrl":"10.1016/j.comnet.2025.111577","url":null,"abstract":"<div><div>Resistance to cyber-attacks is critical for local networks, which are responsible for the smooth operation of many processes such as data sharing, communication, data storage and application access. In this study, a modular system is proposed to detect attacks that may occur in local networks. The proposed model is designed to detect local network attacks using two different methods. The first method aims to detect Spanning Tree Protocol (STP) Root Bridge, MAC Flood, Man in the Middle (MiTM) and Rogue DHCP attacks that are common in local area networks. The Layer 2 Discovery (L2D) application has been developed to detect these attacks in real time, which can lead to major service interruptions and data breaches in local networks. In addition, the developed application offers brand-independent security configurations to network administrators with GPT- 4o support. The another module of the proposed method, a feature selection and machine learning based method is presented for the detection of Distributed Denial of Service (DDoS) attacks occurring in local networks. In the proposed method, the most effective features in the CIC-DDoS2019 dataset are iteratively ranked with the default parameters of the Information Gain Attribute (IGA) algorithm and the Light Gradient Boosting Machine (LGBM) algorithm. A median filter is applied to the best selected features, and then new features are created with time series. The newly obtained data set was classified with the default parameters of the K-NN, RF, 1D-CNN, MLP and LGBM classifiers and the classifier with the highest accuracy result was selected. As a result of the process, the best hyper-parameters of the LGBM classifier that gave the highest result were determined with 10-K cross validation. As a result, the proposed method achieved 95.98 % accuracy and 96 % F1 Score value on the 13-class CIC-DDoS2019 dataset. In the last step of the study, classes consisting of similar characteristics in the dataset were combined and the CIC_DDoS2019 dataset was reduced to 12 classes. The proposed method was applied to the 12-class CIC_DDoS2019 dataset and achieved an accuracy 99.14 % and 99 % F1 Score. In addition to the detection capability of DDoS attacks, the study brings a new perspective to intrusion detection studies with the detection of real-time STP Root Bridge, MAC Flood, Man in the Middle (MiTM) and Rogue DHCP attacks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111577"},"PeriodicalIF":4.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703506","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}

{"title":"A survey of existing attacks on 5G SA","authors":"Mengyi Gong,&nbsp;Ziling Wei,&nbsp;Shuhui Chen,&nbsp;Wanrong Yu,&nbsp;Fei Wang","doi":"10.1016/j.comnet.2025.111545","DOIUrl":"10.1016/j.comnet.2025.111545","url":null,"abstract":"<div><div>Since the release of the Fifth Generation (5G) Stand-alone (SA) standard in 2018, there is a swift and widespread global adoption of 5G SA mobile network. For the present and foreseeable future, 5G technology will remain the core of mobile networks. Like previous generations of mobile networks, 5G networks have encountered numerous security issues during actual deployment and service provision, which have led to various serious impacts. Based on this, this paper systematically analyzes existing attacks targeting the User Equipment (UE), Radio Access Network (RAN), and core network of 5G networks. We propose a simple and effective method to investigate attacks on various parts of 5G networks, classify these attacks, and discuss their implications, causes, and defense solutions in detail. We find that most security issues have been theoretically addressed through defense solutions proposed in academic literature and 3rd Generation Partnership Project (3GPP) specifications. However, whether these solutions have been implemented in existing 5G networks remains to be verified. Through a deep analysis of existing 5G network security issues, this paper also proposes potential directions for future 5G security research, aiming to promote further research in the field of 5G security and enhance the overall security of future mobile networks.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111545"},"PeriodicalIF":4.4,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144696466","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}

{"title":"Joint optimization of data sensing and computing in the air–ground collaborative inference framework: A multi-agent hybrid-action DRL approach","authors":"Xiaokun Fan ,&nbsp;Yali Chen ,&nbsp;Min Liu ,&nbsp;Yuchen Zhu ,&nbsp;Zhongcheng Li","doi":"10.1016/j.comnet.2025.111540","DOIUrl":"10.1016/j.comnet.2025.111540","url":null,"abstract":"<div><div>Unmanned aerial vehicles (UAVs) are increasingly used for surveillance applications to take videos for Points of Interests (PoIs). Then, the sampled video data is fed into deep neural networks (DNNs) for inference. Due to the high computational complexity of DNNs, directly running DNN inference tasks on resource-constrained UAVs is intractable. To alleviate this issue, edge computing provides a promising solution by offloading tasks to the ground edge servers (ESs). However, how to flexibly schedule and tradeoff various resources for high-accuracy and low-delay inference is a challenge, especially in the complex scenario where video data sensing and DNN task processing are tightly coupled. Thus, this paper studies joint optimization for data sensing and computing in the air–ground collaborative inference framework. Specifically, the models for multi-UAV collaborative data sensing and collaborative inference between multiple UAVs and multiple ESs are designed. Then, we formulate an inference delay minimization problem by jointly optimizing UAVs’ 3D trajectories, number of sampled video frames and computation offloading, while satisfying accuracy, UAV energy budget and sensing mission requirements. Considering mixed continuous–discrete optimization variables, we propose a multi-agent proximal policy optimization (MAPPO) algorithm with a hybrid action space, called “MAPPO-HA”, to learn the optimal policies. Finally, simulation results demonstrate that our algorithm can achieve better performance compared with other optimization approaches.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111540"},"PeriodicalIF":4.4,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670879","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}

{"title":"Semantic Edge Computing and Semantic Communications in 6G networks: A unifying survey and research challenges","authors":"Milin Zhang ,&nbsp;Mohammad Abdi ,&nbsp;Venkat R. Dasari ,&nbsp;Francesco Restuccia","doi":"10.1016/j.comnet.2025.111531","DOIUrl":"10.1016/j.comnet.2025.111531","url":null,"abstract":"<div><div>Semantic Edge Computing (SEC) and Semantic Communications (SemComs) have been proposed as viable approaches to achieve real-time edge-enabled intelligence in sixth-generation (6G) wireless networks. On one hand, SemCom leverages the strength of Deep Neural Networks (DNNs) to encode and communicate the semantic information only, while making it robust to channel distortions by compensating for wireless effects. Ultimately, this leads to an improvement in the communication efficiency. On the other hand, SEC has leveraged distributed DNNs to divide the computation of a DNN across different devices based on their computational and networking constraints. Although significant progress has been made in both fields, the literature lacks a systematic view to connect both fields. In this work, we fill the current gap by unifying the SEC and SemCom fields. We summarize the research problems in these two fields and provide a comprehensive review of the state of the art with a focus on their technical strengths and challenges.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111531"},"PeriodicalIF":4.4,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670882","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}

{"title":"MGGPT: A Multi-Graph GPT-enhanced framework for dynamic fraud detection in cryptocurrency networks","authors":"Ansu Badjie ,&nbsp;Grace Mupoyi Ntuala ,&nbsp;Qi Xia ,&nbsp;Jianbin Gao ,&nbsp;Hu Xia","doi":"10.1016/j.comnet.2025.111508","DOIUrl":"10.1016/j.comnet.2025.111508","url":null,"abstract":"<div><div>The rapid increase in cryptocurrency transactions has increased demand for advanced fraud detection systems. Conventional methods are often rigid and do not effectively capture cryptocurrency networks’ intricate temporal and structural patterns, while existing dynamic approaches struggle with incomplete or missing information. To tackle this issue, we present MGGPT, a new hybrid framework that integrates Graph Attention Neural Networks (GAT) with GPT-based transformers to improve fraud detection within cryptocurrency transaction networks. Our approach utilizes temporal graph structures through reachability networks (reach-nets) to derive essential node features, while also directly integrating edge labels into the embedding vectors, and introduces an innovative mechanism for predicting missing information to address the challenges posed by incomplete data in blockchain networks. The model features a dual-perspective learning strategy, employing local graph structures via GAT Networks and global contextual patterns through GPT-based sequence modeling to capture both structural and temporal dynamics in transaction networks. Our MGGPT framework implements a sophisticated edge classification mechanism using Support Vector Machines (SVM) for the final prediction. Experimental findings on actual cryptocurrency transaction datasets indicate superior efficacy in identifying fraudulent patterns, achieving notable improvements of 8.5% AUC, a 10.2% increase in Precision, 29.5% increment in recall, and 20.5% improvement in F1-score. Compared to baseline models such as STA-GT and CTGN, the proposed MGGPT improves the representation of dynamic relationships and faster convergence. Overall, the analysis reveals that our framework is not only more accurate but also more robust and scalable for real-world temporal graph applications. Ultimately, we assessed the robustness of our framework against adversarial attacks to show its practical applications in blockchains.</div></div>","PeriodicalId":50637,"journal":{"name":"Computer Networks","volume":"270 ","pages":"Article 111508"},"PeriodicalIF":4.4,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144663183","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}