Computer Communications最新文献

{"title":"A Homomorphic MAC-based verifiable secure aggregation for federated learning in cloud–edge AIoT","authors":"Shufen Niu ,&nbsp;Weiying Kong ,&nbsp;Lihua Chen ,&nbsp;Xusheng Zhou ,&nbsp;Ning Wang","doi":"10.1016/j.comcom.2025.108271","DOIUrl":"10.1016/j.comcom.2025.108271","url":null,"abstract":"<div><div>The cloud–edge collaborative Artificial Intelligence of Things (AIoT) architecture addresses challenges in managing vast data storage, intelligent information processing, device interconnectivity within the Internet of Things. For its security risks and data privacy, federated learning emerges as a promising solution for ensuring data privacy in AIoT. However, susceptibility to malicious attacks during data transmission poses a significant challenge and a semi-trusted server may deviate from the specified protocol leading to inaccurate aggregation parameters returned to clients. Our proposed solution introduces a federated learning integrity verification scheme based on homomorphic Message Authentication Code (MAC) within a cloud–edge collaborative AIoT architecture. Homomorphic MAC ensures secure aggregation and integrity verification, even when distinct clients possess different keys, emphasizing integrity verification by edge node, contributes to reduced client computing costs. Further verifying of the aggregated parameters by users prevents untrusted transmission from edge node. Leveraging data integrity verification proves effective in mitigating challenges associated with parameter security, especially in scenarios involving inaccurate aggregation of local model parameters within federated learning. Our solution is free bilinear pairing, resulting in a significant reduction in computational overhead. We evaluate accuracy on the MNIST dataset through comparison with the FedAVG plaintext scheme, showing that our approach ensures parameter integrity while maintaining model performance, numerical simulations also confirm its efficiency.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108271"},"PeriodicalIF":4.3,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Delay analysis of BFT consensus : Case study of Narwhal and Bullshark protocols","authors":"Khouloud Hwerbi ,&nbsp;Ichrak Amdouni ,&nbsp;Cédric Adjih ,&nbsp;Leila Azouz Saidane ,&nbsp;Anis Laouiti","doi":"10.1016/j.comcom.2025.108278","DOIUrl":"10.1016/j.comcom.2025.108278","url":null,"abstract":"<div><div>Acknowledging the critical influence of consensus delays on blockchain performance, this paper presents an analytical and simulation-based exploration of delay characteristics in Byzantine Fault Tolerant (BFT) consensus mechanisms. Our focus is on SUI, a blockchain system that employs a Directed Acyclic Graph (DAG) structure to support parallel transaction execution. SUI relies on two integrated protocols: Narwhal, a mempool protocol responsible for efficient block dissemination and DAG construction; and Bullshark, which organizes DAG vertices to produce a consistent total order of transactions without incurring additional communication overhead.</div><div>While our previous work modeled Narwhal’s delay characteristics under various message propagation distributions, this study shifts attention to Bullshark—the protocol responsible for reaching consensus. We propose a probabilistic analytical model that estimates the number of rounds required to reach consensus. In this model, each validator’s decision is treated as a Bernoulli trial, and we apply the binomial distribution to determine the probability of reaching quorum. This framework enables us to analyze the expected delay of the protocol.</div><div>To validate our model, we implemented both Narwhal and Bullshark and conducted extensive simulations. The simulation results show strong agreement with our analytical predictions, confirming the accuracy of our model. For instance, under a Gaussian delay model with mean <span><math><mrow><mi>μ</mi><mo>=</mo><mn>1</mn><mspace></mspace><mi>ms</mi></mrow></math></span> and standard deviation <span><math><mrow><mi>σ</mi><mo>=</mo><mn>0</mn><mo>.</mo><mn>25</mn></mrow></math></span> ms—values representative of short-range wireless communication in real-world IoT or LAN settings <span><span>[1]</span></span>—we predict an average round duration of approximately 3.26 ms. Furthermore, based on our binomial-based model of block commitment, the expected number of rounds to reach consensus is approximately 1 when <span><math><mrow><mi>f</mi><mo>=</mo><mn>10</mn></mrow></math></span>, indicating that blocks typically commit in a single round with high probability.</div><div>To the best of our knowledge, this is the first study to model Bullshark’s consensus process using Bernoulli trials and binomial distributions. Our contributions offer a novel framework for evaluating its efficiency and provide insights that can guide future optimization and scalability efforts for DAG-based BFT protocols.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108278"},"PeriodicalIF":4.3,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Optimizing bandwidth allocation in mmWave/sub-THz cellular networks using maximum flow algorithms","authors":"Kyriakos N. Manganaris ,&nbsp;Panagiotis Promponas ,&nbsp;Aris Tsolis ,&nbsp;Fotis I. Lazarakis ,&nbsp;Kostas P. Peppas","doi":"10.1016/j.comcom.2025.108221","DOIUrl":"10.1016/j.comcom.2025.108221","url":null,"abstract":"<div><div>The exploitation of millimeter wave (mmWave) and sub-Terahertz (sub-THz) bands is expected to be one of the main pillars for the development of future cellular networks due to the high available bandwidth they provide. The existence of Line-of-Sight (LOS) link between a user equipment (UE) and an access point (AP) is a prerequisite for connection establishment in these networks, as the wireless links in these bands are very sensitive to blockage effects. This can be achieved by densifying APs within a network area. An arising challenge is the efficient exploitation of the available bandwidth of a given network. In this paper, the maximization of the number of served UEs in modern mmWave and sub-THz cellular networks is investigated and achieved by deploying a Maximum Flow Algorithm for UE-AP association (MFUA) to optimize bandwidth allocation, assuming that every AP will have a finite and predefined amount of bandwidth which they can share among UEs. MFUA determines the maximum flow between two given nodes of a graph corresponding to a specific network, where the capacity of its edges is known. An extensive simulation campaign was carried out revealing that the use of MFUA utilizes bandwidth more effectively compared to the reference method and improves the system performance, leading to the maximization of number of served UEs. The examined test cases include static and time-evolving scenarios.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108221"},"PeriodicalIF":4.5,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"ILoRa: Interleaving-driven neural network for rate adaptation in LoRa communications","authors":"Xiaoke Qi ,&nbsp;Haiyang Li ,&nbsp;Dian Zhang ,&nbsp;Lu Wang","doi":"10.1016/j.comcom.2025.108287","DOIUrl":"10.1016/j.comcom.2025.108287","url":null,"abstract":"<div><div>Rate adaptation in LoRa communications is crucial for improving the channel throughput by adjusting the data rate according to varying channel conditions. Existing methods typically operate at the packet or symbol level, which limits their ability to achieve fine-grained rate adaptation. In this paper, we propose ILoRa, an Interleaving-driven partial transmission method that automatically adjusts transmission rates according to real-time channel conditions. To be specific, we first introduce intra-symbol interleaving that leverages a progressive inorder traversal method to determine the transmission order within a symbol. Then inter-symbol interleaving is applied to coordinate the order across symbols. To manage the interleaving-induced partial transmission and improve communication performance under noisy conditions, we employ a multi-task convolutional recurrent neural network (MT-CRNN). This network leverages advanced data augmentation methods to further enhance channel robustness: time-spectral augmentation to mitigate information loss and synthetic noisy data to simulate various channel conditions. Extensive experimental results demonstrate that ILoRa significantly enhance transmission efficiency while maintaining reliable performance even in challenging environments.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108287"},"PeriodicalIF":4.5,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Efficient security service function chaining based on federated learning in edge networks","authors":"Yunjian Jia,&nbsp;Jian Yu,&nbsp;Liang Liang,&nbsp;Fang Fang,&nbsp;Wanli Wen","doi":"10.1016/j.comcom.2025.108285","DOIUrl":"10.1016/j.comcom.2025.108285","url":null,"abstract":"<div><div>The escalating demand for network services has prompted the evolution of Service Function Chaining (SFC) within 6G networks to deliver sophisticated, customized services while ensuring robust cybersecurity. This paper introduces an efficient and secure framework for SFC in Mobile Edge Computing (MEC) environments, termed the Federated Learning-based SFC (FL-SFC), which integrates SFC, MEC, and Federated Learning (FL) to enhance service policy decision-making and safeguard user privacy. The FL-SFC framework enables dynamic updating of service policies and optimizes communication efficiency. We propose an anomaly detection model, CNN-GRU, which combines Convolutional Neural Networks (CNNs) and Gated Recurrent Units (GRUs) to significantly improve anomaly detection performance at the network edge. Additionally, to address the high communication costs associated with service policy models, we have designed a model compression mechanism leveraging sparsification and quantization techniques, which substantially reduces communication overhead during model training. Simulation experiments demonstrated the superiority of the FL-SFC framework and the CNN-GRU model in detection performance over existing methods. Results indicate that our model excels in accuracy, precision, recall, and F1-score while significantly reducing the number of communication bits, thereby validating the effectiveness of our approach.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108285"},"PeriodicalIF":4.5,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 slot-based energy storage decision-making approach for optimal Off-Grid telecommunication operator","authors":"Youssef Ait El Mahjoub ,&nbsp;Jean-Michel Fourneau","doi":"10.1016/j.comcom.2025.108273","DOIUrl":"10.1016/j.comcom.2025.108273","url":null,"abstract":"<div><div>This paper proposes a slot-based energy storage approach for decision-making in the context of an Off-Grid telecommunication operator. We consider network systems powered by solar panels, where harvest energy is stored in a battery that can also be sold when fully charged. To reflect real-world conditions, we account for non-stationary energy arrivals and service demands that depend on the time of day, as well as the failure states of PV panel. The network operator we model faces two conflicting objectives: maintaining the operation of its infrastructure and selling (or supplying to other networks) surplus energy from fully charged batteries. To address these challenges, we developed a slot-based Markov Decision Process (MDP) model that incorporates positive rewards for energy sales, as well as penalties for energy loss and battery depletion. This slot-based MDP follows a specific structure we have previously proven to be efficient in terms of computational performance and accuracy. From this model, we derive the optimal policy that balances these conflicting objectives and maximizes the average reward function. Additionally, we present results comparing different cities and months, which the operator can consider when deploying its infrastructure to maximize rewards based on location-specific energy availability and seasonal variations. Experimental results show that our proposed algorithm outperforms classical methods in large-scale scenarios. While Relative Value Iteration algorithm remains competitive on smaller instances, its convergence time increases significantly under strict precision requirements (e.g., <span><math><mrow><mi>ϵ</mi><mo>&lt;</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>10</mn></mrow></msup></mrow></math></span>). In contrast, our method maintains both speed and robustness, solving MDPs with up to <span><math><mrow><mn>2</mn><mspace></mspace><mo>×</mo><mspace></mspace><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mn>5</mn></mrow></msup></mrow></math></span> states and 100 actions in under one hour, whereas standard approaches exceed <span><math><mrow><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mn>4</mn></mrow></msup></mrow></math></span> seconds.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108273"},"PeriodicalIF":4.5,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Correctness of flow migration across Network Function instances","authors":"Ranjan Patowary ,&nbsp;Gautam Barua ,&nbsp;Radhika Sukapuram","doi":"10.1016/j.comcom.2025.108284","DOIUrl":"10.1016/j.comcom.2025.108284","url":null,"abstract":"<div><div>Network Functions (NFs) improve the safety and efficiency of networks. Flows traversing NFs may need to be migrated from a source NF instance (sNF) to a destination NF instance (dNF) to balance load, conserve energy, etc. When NFs are stateful, the information stored on an sNF per flow must be migrated to the corresponding dNF before the flow is migrated, to avoid problems of consistency. Our main contribution is to examine what it means to correctly migrate flows from a stateful NF instance. We define the property of Weak-O, where only the state information required for packets to be correctly forwarded from an sNF is migrated first to the corresponding dNF, while the remaining states are eventually migrated. Weak-O can be preserved without buffering or dropping packets, unlike existing algorithms. We propose an algorithm that preserves Weak-O and prove its correctness. Even though this may cause packet re-ordering, we experimentally demonstrate that the goodputs with and without migration are comparable when the old and new paths have the same delays and bandwidths. This is also true when the new path has larger bandwidth or at most 5 times longer delays. Thus flow migration without buffering is practical, contrary to what was thought before. We also prove that no criterion stronger than Weak-O can be preserved in a flow migration system that requires no buffering or dropping of packets and eventually synchronizes its states.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108284"},"PeriodicalIF":4.5,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 lightweight secret-sharing-based defense against model poisoning attacks in privacy-preserving federated learning","authors":"Hengheng Xiong,&nbsp;Jiguang Lv,&nbsp;Dapeng Man,&nbsp;Yukun Zhu,&nbsp;Tao Liu,&nbsp;Huanran Wang,&nbsp;Chen Xu,&nbsp;Wu Yang","doi":"10.1016/j.comcom.2025.108272","DOIUrl":"10.1016/j.comcom.2025.108272","url":null,"abstract":"<div><div>As Artificial Intelligence of Things (AIoT) converges with Privacy-Preserving Federated Learning (PPFL), the challenge of defending against model poisoning attacks emerges as increasingly critical. Due to PPFL’s cryptographic protocols for protecting gradient exchanges, detecting poisoning attacks becomes challenging. Traditional defense mechanisms rely on plaintext gradient analysis and thus cannot be directly applied to encrypted gradients. Although homomorphic encryption-based defense schemes enable secure computations on encrypted data, their substantial computational overhead makes them impractical for resource-constrained Internet of Things (IoT) deployments. To address these challenges, we propose a Secret-Sharing-based Defense Framework (SSDF), a lightweight scheme that enables efficient similarity calculations on encrypted gradients under secure aggregation protocols. Our scheme facilitates robust aggregation of encrypted parameters in resource-constrained edge computing environments while protecting the privacy of local model updates. Extensive experiments on four datasets demonstrate that our proposed scheme provides robust defense capabilities against poisoning attacks for both Independent and Identically Distributed (IID) and non-IID data.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108272"},"PeriodicalIF":4.5,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"ACSFL: An adaptive client selection-based Federated Learning with personalized differential privacy for heterogeneous AIoT environments","authors":"Zhousheng Wang ,&nbsp;Junjie Chen ,&nbsp;Hua Dai ,&nbsp;Jian Xu ,&nbsp;Geng Yang ,&nbsp;Hao Zhou","doi":"10.1016/j.comcom.2025.108264","DOIUrl":"10.1016/j.comcom.2025.108264","url":null,"abstract":"<div><div>Driven by the rapid development of Artificial Intelligence (AI) and the Internet of Things (IoT), the Artificial Intelligence of Things (AIoT) is increasingly applied in smart environments. Federated Learning (FL) meets the need for intelligent data processing in these environments by providing powerful training capabilities while preserving privacy. However, AIoT environments pose new challenges for FL, particularly due to the heterogeneity of edge devices, which vary in hardware, software, network conditions, and data distribution. These factors degrade model performance and hinder convergence. Additionally, communication overhead and data privacy risks are also critical concerns. Although Differential Privacy (DP) can offer protection, they often apply uniform privacy levels, overlooking the diversity of AIoT devices. On the other hand, while current client-selection approaches partially address the heterogeneity of AIoT devices, they also tend to ignore the impact of the noising mechanisms. In this paper, we propose ACSFL, an adaptive client selection-based FL framework that integrates personalized local DP. By a novel, dynamic evaluation metric of node heterogeneity, privacy budget, and contribution, ACSFL can jointly optimize model performance, privacy preservation, and communication efficiency. We further propose a personalized local differential privacy mechanism in ACSFL, to filter and allocate each client’s budget per round, substantially enhancing privacy preservation and yielding significant accuracy gains under identical overall privacy constraints. All the above assertions are also well supported by theoretical and experimental demonstration. Specifically, our experiments show that ACSFL improves model convergence and generalization by 14% on average, achieves comparable model accuracy with 20% fewer clients, reduces communication overhead by over 25%, and saves about 26% of the privacy budget compared to other client selection methods.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108264"},"PeriodicalIF":4.5,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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":"Overcoming data limitations in internet traffic forecasting: LSTM models with transfer learning and wavelet augmentation","authors":"Sajal Saha ,&nbsp;Anwar Haque ,&nbsp;Greg Sidebottom","doi":"10.1016/j.comcom.2025.108280","DOIUrl":"10.1016/j.comcom.2025.108280","url":null,"abstract":"<div><div>Accurate internet traffic prediction in smaller ISP networks is challenged by limited data availability. This paper explores this issue using transfer learning and data augmentation techniques with two LSTM-based models, LSTMSeq2Seq and LSTMSeq2SeqAtn, initially trained on a comprehensive dataset provided by Juniper Networks, Inc. and subsequently applied to smaller datasets. The datasets represent real internet traffic telemetry, offering insights into diverse traffic patterns across different network domains. Our study found that although both models performed well in single-step predictions, multi-step forecasting was more challenging, especially regarding long-term accuracy. Empirical results demonstrated that LSTMSeq2Seq outperformed LSTMSeq2SeqAtn on smaller datasets, with improvements in forecasting accuracy by up to 36.70% in MAE and 27.66% in WAPE after applying data augmentation using Discrete Wavelet Transform. The LSTMSeq2Seq model achieved an accuracy improvement from 83% to 88% for 6-step forecasts, 82% to 88% for 9-step forecasts, and 81% to 87% for 12-step forecasts, whereas LSTMSeq2SeqAtn exhibited a more stable short-term performance but higher variability in longer forecasts. Additionally, the mean absolute percentage error (MAPE) of multi-step predictions increased over longer horizons, with LSTMSeq2Seq reaching 6.74% at 12 steps and LSTMSeq2SeqAtn at 6.77%, highlighting the challenge of long-term forecasting. Variability analysis showed that while the attention mechanism in LSTMSeq2SeqAtn improved short-term prediction consistency, it also increased uncertainty in longer forecasts, as seen in the interquartile range (IQR) rising from 0.578 at 6 steps to 1.237 at 9 steps. Outlier analysis further confirmed that LSTMSeq2Seq exhibited more stable improvements, whereas LSTMSeq2SeqAtn showed increased dispersion in forecast accuracy. These findings underscore the importance of transfer learning and data augmentation in enhancing forecasting accuracy, particularly for smaller ISP networks with limited data availability. Furthermore, our analysis highlights the trade-offs between model complexity, short-term consistency, and long-term stability in internet traffic prediction.</div></div>","PeriodicalId":55224,"journal":{"name":"Computer Communications","volume":"242 ","pages":"Article 108280"},"PeriodicalIF":4.3,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144722762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}