Ngangbam Indrason;Wanbanker Khongbuh;Kalyan Baital;Goutam Saha
{"title":"MBCSD-IoT: A Multi-Level Blockchain-Assisted SDN-Based IoT Architecture for Secured E-Voting System","authors":"Ngangbam Indrason;Wanbanker Khongbuh;Kalyan Baital;Goutam Saha","doi":"10.1109/TNSE.2025.3535726","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3535726","url":null,"abstract":"For designing a reliable voting mechanism, the present study undertook an investigation to design a secured and automated e-voting infrastructure namely MBCSD-IoT. For this purpose, a multi-level voting architecture has been designed where most of the nodes consist of Blockchain-assisted SDN-based IoT infrastructure where Blockchain has been embedded in the said IoT system to provide reliable security. In MBCSD-IoT, four levels of hierarchies have been designed namely Booth, District, State and Country Level layers. An Electronic Voting Machine (EVM) is designed which is equipped with suitable security systems like Elliptic Curve Cryptography (ECC) and hash functions. This multiple hierarchical infrastructure will ensure secured storage of voting data using blockchain at multiple levels. Here, voter authentication is automated using biometric inputs. Automated counting of votes is executed at the top-most level of the hierarchy which helps to save extra expenditure. The past literature investigation reveals insignificant number of works in this direction. The present work ensures a suitable infrastructure for implementing a better-secured voting process in large democracy. The whole system has been designed and tested in architectural point of view both in simulation and testbed considering all the security aspects. Experimental results obtained ensured satisfactory performance with respect to throughput, latency, and packet loss.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1613-1622"},"PeriodicalIF":6.7,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870951","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":"Degradation Estimation for Distributed Nonlinear Systems: A PDF-Consensus Particle Filtering Method","authors":"Chulin Zhou;Shiyou Chen;Chaoyang Wang","doi":"10.1109/TNSE.2025.3530158","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3530158","url":null,"abstract":"In this article, a distributed probability density function (PDF)-consensus particle filter (PF) algorithm for a class of network systems with degradation is discussed. In order to consider the interaction between component-level degradation and system state, the degradation modelling framework is developed by combining the stochastic degradation process and the state transition model of the system. And the dynamics of the degradation model are described in terms of a Wiener-based process to emphasize the evolution of degradation over time. To reach consensus on the local posterior PDFs at each node in the sense of relative entropy and reduce the communication burden, the state space of the system is divided by a group of weighted grids. Then, the local PDFs are approximated with a combination of the indicator functions and exchange the parameters with neighboring nodes. In order to obtain the particle representation of the fused PDFs, a new importance sampling function is developed to fuse the local grid-based PDFs and to enhance the compatibility of particles with neighboring nodes. A numerical example on target tracking is provided to demonstrate the effectiveness of the proposed scheme.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1408-1419"},"PeriodicalIF":6.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471801","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}
Gang He;Yanli Ren;Jun Zhao;Guorui Feng;Xinpeng Zhang
{"title":"EPCNN: Efficient and Practical Privacy-Preserving Convolutional Neural Network Inference","authors":"Gang He;Yanli Ren;Jun Zhao;Guorui Feng;Xinpeng Zhang","doi":"10.1109/TNSE.2025.3534834","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3534834","url":null,"abstract":"Convolutional Neural Networks (CNNs), as a powerful tool for efficient inference, have rapidly developed into a Machine Learning as a Service paradigm facilitated by cloud computing. Nevertheless, this service model raises privacy concerns, particularly in scenarios where relying on two non-colluding servers is unfeasible. To address this issue, we present EPCNN, an Efficient and Practical CNN inference scheme, which concurrently ensures data privacy, model privacy, and inference results with only a single server. EPCNN leverages Paillier homomorphic encryption for secure convolution operations on encrypted data and involves minimal client-server interactions. The client only participates in evaluating non-linear activation functions by judging the signs of blinded convolution results to streamline the interactions and enhance the system's practicality. Our security analysis validates the reliability of the proposed scheme, while experimental results demonstrate high inference accuracy comparable to plaintext-based methods. Compared to the state-of-the-art work, EPCNN attains huge improvements in both runtime and communication overhead.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1567-1580"},"PeriodicalIF":6.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871013","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}
Wenyue Sun;Qian Chen;Xuehua Song;Elisa Bertino;Changda Wang
{"title":"Network Traffic Matrix Estimation Based on Link Loads Sampling","authors":"Wenyue Sun;Qian Chen;Xuehua Song;Elisa Bertino;Changda Wang","doi":"10.1109/TNSE.2025.3533745","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3533745","url":null,"abstract":"Traffic Matrix (TM) represents traffic between all Origin-Destination (OD) node pairs in a network, playing a crucial role in network management. While the methods for TM acquisition typically require scaling each link load in a network, measurement costs arise drastically as the number of links grows exponentially with the number of nodes. To address this issue while achieving TM with acceptable accuracy aligned with various network management requirements, the paper proposes two novel methods. The first is the ME-TMEIM (TM Estimation with Incomplete Measurement Based on Maximum Entropy) method, an efficient approach with yet acceptable accuracy. The second is the D-TMEIM (Dynamic TMEIM) method. Compared to the ME-TMEIM method, the D-TMEIM method trades the TM's acquisition accuracy for efficiency. It adds temporal constraints on network traffic to improve the precision of the obtained missing link loads, based on which the TM is generated using the CS-OMP (Compressed Sensing-Orthogonal Matching Pursuit) algorithm. Experimental results using publicly available Abilene and GÉANT networks demonstrate that the proposed methods not only enhance TM acquisition efficiency but also maintain nearly the same accuracy as the known methods that acquire TM through exhaustive links measurement.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1524-1539"},"PeriodicalIF":6.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871063","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}
Zhijiong Wang;Anguo Zhang;Hung Chun Li;Yadong Yin;Wei Chen;Chan Tong Lam;Peng Un Mak;Mang I Vai;Yueming Gao;Sio Hang Pun
{"title":"DFE: Deep Flow Embedding for Robust Network Traffic Classification","authors":"Zhijiong Wang;Anguo Zhang;Hung Chun Li;Yadong Yin;Wei Chen;Chan Tong Lam;Peng Un Mak;Mang I Vai;Yueming Gao;Sio Hang Pun","doi":"10.1109/TNSE.2025.3535577","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3535577","url":null,"abstract":"People's increasing demand for high-quality network services has prompted the continuous attention and development of network traffic classification (NTC). In recent years, deep flow inspection (DFI) is considered to be the most effective and promising method to solve the NTC. However, DFI still cannot effectively address the problem of changes in flow characteristics of complex packet flows and the discovery of new traffic categories. In this paper, we propose a metric learning based deep learning solution with feature compressor, named deep flow embedding (DFE). The feature compressor is used to compress the feature information transmitted layer by layer in DL backbone while maintaining the computational accuracy, so that the backbone can remove as much noise, redundancy, and other irrelevant information from the input data as possible, and achieve more robust feature extraction of network traffic flow. The deep learning (DL) backbone generates an embedding vector for each network packet flow. Then the embedding vector is compared with the vector template preset for each traffic type in the template library to determine the category of the packet flow. Experimental results verify that our method is more effective than the traditional DFI methods in overcoming the problems of flow characteristics variation and new category discovery.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1597-1612"},"PeriodicalIF":6.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871058","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 Multi-UAV Network Formation Scheme via Integrated Localization and Motion Planning","authors":"Kai Ma;Hanying Zhao;Jian Wang;Yu Wang;Yuan Shen","doi":"10.1109/TNSE.2025.3534623","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3534623","url":null,"abstract":"High-accuracy localization and formation are essential for multi-UAV networks to perform cooperative tasks. However, the joint design of localization and motion planning is challenging due to complex information coupling effects, which leads to a loss of formation accuracy. In this paper, we establish an integrated localization and motion planning scheme for multi-UAV networks. First, we derive bounds for the relative formation error, which reveals how measurement and motion noises affect the formation accuracy. Then, we propose a bidirectional process framework to enhance the formation accuracy. The forward process presents a near-optimal motion planning algorithm that leverages the equivalence relation of relative formations to mitigate the impact of localization uncertainties. The backward process addresses bandwidth allocation and UAV activation to maximize formation accuracy. Numerical results verify the gains of the proposed integrated scheme in formation accuracy.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1552-1566"},"PeriodicalIF":6.7,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871012","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":"Multi-Orbit Circumnavigation Control of UAVs With Arbitrary Angular Spacing in Three-Dimensional Space","authors":"Yanhong Luo;Zhen Wang;Huaguang Zhang;Xiangpeng Xie","doi":"10.1109/TNSE.2025.3534421","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3534421","url":null,"abstract":"In this paper, a novel multi-orbit circumnavigation control law is proposed for a group of UAVs with arbitrary angular spacing based on local information. By constructing the actual relative velocity and the ideal relative velocity in three dimensional space, the circumnavigation control problem of moving target is first transformed into a relative velocity tracking problem. Further, to remove the limitation that the UAVs require the global information of the moving target, the corresponding fixed-time convergent estimators with the cyclic directed graph are developed. Based on these distributed estimators and relative kinematics equations, the dynamic linear feedback is introduced to derive the distributed control law. At the same time, the angular spacing update law and the circumnavigation radius coefficient are designed, so that the UAVs can circumnavigate on multi-orbit with any angular spacing. Finally, the exponential stability of the control law is proved by Lyapunov method, and the effectiveness of the control law is verified by five examples.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1540-1551"},"PeriodicalIF":6.7,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871062","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}
Yang Shi;Minyu Teng;Jingwen Liang;Jingxuan Han;Jiayao Gao;Guoyue Xiong;Xiaoping Wang;Hongfei Fan
{"title":"Intrusion-Resilient Undetachable Signature for Mobile-Agent-Based Collaborative Commerce Systems","authors":"Yang Shi;Minyu Teng;Jingwen Liang;Jingxuan Han;Jiayao Gao;Guoyue Xiong;Xiaoping Wang;Hongfei Fan","doi":"10.1109/TNSE.2025.3532691","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3532691","url":null,"abstract":"Mobile agents are valuable in collaborative commerce systems due to their mobility and autonomy, enabling them to traverse the Internet and purchase goods and services on behalf of their owners. However, in the face of potential attacks from malicious hosts, securely executing a contract on behalf of the original signer poses a significant challenge. In this paper, we propose an Intrusion-Resilient Undetachable Signature (IRUS) approach for mitigating security risks associated with signing key leakage on the signer's host, base device, and even potentially malicious remote hosts. Additionally, it addresses the risk of signing algorithm misuse on remote hosts. Our approach ensures that adversaries cannot forge past or future signatures as long as the base device remains secure, even if the current signing key is compromised. In cases where the base device is compromised, although future signatures may be forged, all past signatures remain secure. Furthermore, we integrate the encrypted signing function with the original signer's requirements to prevent the misuse of the signing algorithm and the exposure of the original signing key on malicious hosts. Security proofs have confirmed that our scheme can effectively defend against various types of attacks, and experimental evaluations have demonstrated the strong performance of the proposed approach with enhanced security, meanwhile reducing the execution times of the signing phase by at most 75% and the verification phase by 95% compared with three existing undetachable signature schemes.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1510-1523"},"PeriodicalIF":6.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870968","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 Hybrid Semi-Asynchronous Federated Learning and Split Learning Strategy in Edge Networks","authors":"Neha Singh;Mainak Adhikari","doi":"10.1109/TNSE.2025.3530999","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3530999","url":null,"abstract":"Federated Learning (FL) is an emerging technique that involves training Machine/Deep Learning models over distributed Edge Devices (EDs) while facing three challenges: device heterogeneity, resource-constraint devices, and Non-IID (Non-Identically Independently Distributed). In the standard FL, the centralized server has to wait for the model parameters from the slowest participating EDs for global training, which leads to increased waiting time due to device heterogeneity. Asynchronous FL resolves the issue of device heterogeneity, however, it requires frequent model parameter transfer, resulting in a straggler effect. Further, frequent asynchronous updates over Non-IID in participating EDs can affect training accuracy. To overcome the challenges, in this paper, we present a new Federated Semi-Asynchronous Split Learning (Fed-SASL) strategy. Fed-SASL utilizes semi-asynchronous aggregation, where model parameters are aggregated in a centralized cloud server, and received from participating EDs without waiting for all devices. This strategy significantly reduces training time and communication overhead. Additionally, split learning is employed to handle slow EDs by dividing the neural network model based on the computational loads of devices, thereby reducing the burden on stragglers. Extensive simulation results over real-time testbed and one benchmark dataset demonstrate the effectiveness of the proposed strategy over existing ones.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 2","pages":"1429-1439"},"PeriodicalIF":6.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471800","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":"Estimator-Based Dual-Model Predictive Control for Multi-AAVs With Connectivity-Preserving","authors":"Zhixu Du;Hao Zhang;Zhuping Wang;Huaicheng Yan","doi":"10.1109/TNSE.2025.3532475","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3532475","url":null,"abstract":"This paper investigates a distributed control problem for maintaining connectivity and avoiding collisions among multiple autonomous aerial vehicles (AAVs). A novel distributed estimator is proposed for AAVs. The following AAVs utilize information from their neighbors to estimate the output information of all AAVs. By incorporating a connectivity maintenance function and a collision-free potential field function, the following AAVs avoid collisions with each other and obstacles while maintaining network connectivity. A dual-model predictive control (dual-MPC) algorithm for AAVs, referred to as outer-loop and inner-loop model predictive control optimization, is designed to quickly track the leading AAV. Stability and feasibility of the dual-MPC algorithm can be ensured by uniting rolling optimization with fuzzy logic systems. Finally, the simulation results confirm the effectiveness of the proposed controller.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"1482-1496"},"PeriodicalIF":6.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870989","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}