IEEE Transactions on Network Science and Engineering最新文献_第5页

MADDPG-M&L: UAV-Assisted Joint User Association and Slicing Resource Allocation in HetNets 无人机辅助下HetNets联合用户关联与分层资源分配

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-26 DOI: 10.1109/TNSE.2025.3554991

Geng Chen;Fang Sun;Hongjia Liang;Qingtian Zeng;Yu-Dong Zhang

{"title":"MADDPG-M&L: UAV-Assisted Joint User Association and Slicing Resource Allocation in HetNets","authors":"Geng Chen;Fang Sun;Hongjia Liang;Qingtian Zeng;Yu-Dong Zhang","doi":"10.1109/TNSE.2025.3554991","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554991","url":null,"abstract":"With the increasing diversity of use cases and service requirements in heterogeneous networks, the concept of network slicing has emerged. However, user association, distributed resource allocation, and the high-speed data rate demands of different users still face numerous challenges. To address these issues, we propose a UAV-assisted RAN resource slicing framework in heterogeneous networks. Firstly, we employ a stable matching game algorithm to solve the access problem between UAVs (unmanned aerial vehicles) and TBSs (terrestrial base stations). Secondly, we formulate a joint user association and slicing resource allocation problem. However, the optimization problem is non-convex, and the problem is decoupled into two sub-problems: user association and slicing resource allocation. Moreover, a Lagrangian dual algorithm is employed to solve the user association problem, while Multi-Agent Deep Deterministic Policy Gradient based on Matching Game and Lagrangian Dual (MADDPG-M&L) slicing resource allocation algorithm is proposed to determine the allocation ratio of resources for each slice. Simulation results show that the Lagrangian dual-based user association algorithm improves the system performance by 12.8%, 36.2% and 61.9% respectively compared to the other three user association methods. Furthermore, compared to MATD3-M&L, MASAC-M&L, and Hard-slicing, the proposed MADDPG-M&L algorithm improves the throughput by 36.3%, 105%, and 177%, respectively. In terms of latency, the improvements are 46%, 68%, and 86.7%, respectively. For SINR, the increases are 5.2%, 2.9%, and 6.4%, respectively. The objective function improves by 54.7%, 218%, and 336%, respectively, with the data transmission rate showing the most significant improvement.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2878-2894"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492277","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

Robust Finite-Time Containment of Networked Heterogeneous Nonlinear Systems With Intermittent Measurement Only 仅含间歇测量的网络非均匀非线性系统的鲁棒有限时间约束

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-26 DOI: 10.1109/TNSE.2025.3554592

Biao Tian;Hao Zhang;Peiyu Cui;Zhuping Wang;Huaicheng Yan

{"title":"Robust Finite-Time Containment of Networked Heterogeneous Nonlinear Systems With Intermittent Measurement Only","authors":"Biao Tian;Hao Zhang;Peiyu Cui;Zhuping Wang;Huaicheng Yan","doi":"10.1109/TNSE.2025.3554592","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554592","url":null,"abstract":"The robust finite-time containment problem of fully heterogeneous multiagent systems with uncertainties is often challenging, especially when only intermittent output measurement is used. To address the issue posed by the nonidentical system dynamics of multiple leaders, which makes the traditional distributed estimator form for the convex hull inapplicable, a distributed finite-time estimator is constructed for each follower to extract the system matrices and states of leaders. Then, in the output-triggering setting, a finite-time extended state observer driven by intermittent output measurement is developed to reconstruct the uncertainties and unmeasurable states of followers. Meanwhile, the non-continuous output measurement will lead to the differentiation of virtual control laws undefined. To solve this issue, a filtering compensation scheme-based finite-time controller via the backstepping technique is developed for nonlinear followers, ensuring practical finite-time stability (PFTS) of the closed-loop system. It is shown that the proposed algorithm steers each follower into the preset convex combination spanned by the positions of multiple leaders. The capability of the exploited control protocol is verified through simulations and experiments.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2823-2834"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492224","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

Game-Theoretic Protection Adoption Against Networked SIS Epidemics 针对网络化SIS流行病的博弈论保护措施

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-26 DOI: 10.1109/TNSE.2025.3554807

Abhisek Satapathi;Ashish R. Hota

{"title":"Game-Theoretic Protection Adoption Against Networked SIS Epidemics","authors":"Abhisek Satapathi;Ashish R. Hota","doi":"10.1109/TNSE.2025.3554807","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554807","url":null,"abstract":"In this paper, we investigate game-theoretic strategies for containing spreading processes on large-scale networks. Specifically, we consider the class of networked susceptible-infected-susceptible (SIS) epidemics where a large population of agents strategically choose whether to adopt partially effective protection. We define the utilities of the agents which depend on the degree of the agent, its individual infection status and action, as well as the the overall prevalence of the epidemic and strategy profile of the entire population. We further present the coupled dynamics of epidemic evolution as well as strategy update which is assumed to follow the replicator dynamics. By relying on timescale separation arguments, we first derive the game-theoretic protection adoption strategies of the agents for a given epidemic state, and then present the reduced epidemic dynamics. The existence and uniqueness of endemic equilibrium is rigorously characterized and forms the main result of this paper. We then present extensive numerical results to highlight the impacts of heterogeneous node degrees, infection rates, cost of protection adoption, and effectiveness of protection on the epidemic prevalence at the equilibrium. Finally, we illustrate the evolution of the networked SIR epidemic under game-theoretic protection adoption.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2863-2877"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10938930","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive Nash Equilibrium Seeking in Hybrid Heterogeneous Open Multi-Agent Systems Under DoS Attacks DoS攻击下混合异构开放多智能体系统的自适应纳什均衡寻求

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-24 DOI: 10.1109/TNSE.2025.3553900

Shuting Chen;Ying Wan;Jinde Cao

{"title":"Adaptive Nash Equilibrium Seeking in Hybrid Heterogeneous Open Multi-Agent Systems Under DoS Attacks","authors":"Shuting Chen;Ying Wan;Jinde Cao","doi":"10.1109/TNSE.2025.3553900","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3553900","url":null,"abstract":"This paper investigates the problem of adaptive Nash equilibrium (NE) seeking in hybrid heterogeneous open multi-agent systems (MASs) under Denial-of-Service (DoS) attacks. In the considered open MASs, agents can join or leave the network at any time, which leads to a changeable system size. To address this challenge, we propose a fully distributed control framework that enables agents with heterogeneous dynamics to converge to NE at an exponential rate, using only limited information exchange and localized computation. Additionally, an adaptive strategy is introduced, where the control gains of each agent are adjusted based on local adjacent information. This adjustment allows the system to adapt in real-time to environmental changes. We establish sufficient conditions for the existence of NE in both fixed and varying agent numbers, even in the presence of DoS attacks. Through rigorous theoretical analysis, the proposed adaptive algorithm is proven to guarantee the convergence of the hybrid heterogeneous MAS to the NE despite sustained or intermittent DoS attacks. Numerical simulations are provided to demonstrate the effectiveness of the proposed framework for open MASs in adversarial environments.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2770-2782"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492249","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

UAV-NIDD: A Dynamic Dataset for Cybersecurity and Intrusion Detection in UAV Networks UAV- nidd：用于无人机网络安全和入侵检测的动态数据集

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-24 DOI: 10.1109/TNSE.2025.3553442

Hassan Jalil Hadi;Yue Cao;Muhammad Khurram Khan;Naveed Ahmad;Yulin Hu;Chao Fu

{"title":"UAV-NIDD: A Dynamic Dataset for Cybersecurity and Intrusion Detection in UAV Networks","authors":"Hassan Jalil Hadi;Yue Cao;Muhammad Khurram Khan;Naveed Ahmad;Yulin Hu;Chao Fu","doi":"10.1109/TNSE.2025.3553442","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3553442","url":null,"abstract":"UAVs are necessary for numerous tasks but are vulnerable to cyber threats due to their widespread use and connectivity. The lack of a comprehensive dataset necessitates the development of effective detection and mitigation solutions. Our work introduces UAV-NIDD, a new dataset that addresses the gaps in understanding and countering both cyber and physical threats in UAV networks. It includes three distinct attack scenarios: compromised UAV initiating a network-wide attack, access point compromised network-wide intrusion, and compromised Ground Control Station (GCS) establishing a network-wide attack. We develop a real-time testbed for creating UAV-NIDD (Unmanned Aerial Vehicles-Network Intrusion Detection Dataset), incorporating UAV devices, data collection tools, and controllers. Our testbed facilitates cyber-attack execution and data gathering under normal and attack conditions. Our dataset covers various cyber-attacks like Scanning, Reconnaissance, DoS, DDoS, GPS Jamming & Spoofing, MITM, Replay, Evil Twin, Brute-Force, and Fake Landing packet attacks. Additionally, UAV-NIDD presents a valuable resource for AI and ML solutions, strengthening UAV networks against evolving cyber threats. Moreover, we offer open access and cooperative innovation in terms of long-term updating of dataset.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2739-2757"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492409","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

Graph-Tensor FISTA-Net: Edge Computing-Aided Deep Learning for Distributed Traffic Data Recovery 图张量FISTA-Net：边缘计算辅助深度学习的分布式交通数据恢复

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-24 DOI: 10.1109/TNSE.2025.3554634

Lei Deng;Xiao-Yang Liu;Haifeng Zheng;Xinxin Feng;Ming Zhu;Danny H. K. Tsang

{"title":"Graph-Tensor FISTA-Net: Edge Computing-Aided Deep Learning for Distributed Traffic Data Recovery","authors":"Lei Deng;Xiao-Yang Liu;Haifeng Zheng;Xinxin Feng;Ming Zhu;Danny H. K. Tsang","doi":"10.1109/TNSE.2025.3554634","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554634","url":null,"abstract":"In intelligent transportation systems, deep learning is a widely adopted technique for traffic data recovery. In city-wide traffic data recovery tasks, traditional centralized deep-learning-model training strategies become inapplicable because of the expensive storage costs for large-scale traffic datasets. In this scenario, edge computing emerges as a natural choice, allowing decentralized data storage and distributed training on edge nodes. However, there is still a challenge: distributed training on edge nodes suffers from high communication costs for parameter transmission. In this paper, we propose a communication-efficient Graph-Tensor Fast Iterative Shrinkage-Thresholding Algorithm-based neural Network (GT-FISTA-Net) for distributed traffic data recovery. Firstly, we model the recovery task as a graph-tensor completion problem to better capture the low-rankness of traffic data. A recovery guarantee is also provided to characterize the performance bounds of the proposed scheme in terms of recovery error. Secondly, we propose a distributed graph-tensor completion algorithm and unfold it into a deep neural network called GT-FISTA-Net. GT-FISTA-Net requires small communication costs for distributed model training on edge nodes and thus it is applicable for city-wide traffic data recovery. Extensive experiments on real-world datasets show that the proposed GT-FISTA-Net can also provide excellent recovery accuracy compared with state-of-the-art distributed recovery methods.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2835-2847"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492313","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

Efficient Off-Chain Data Feed Mechanism Using a Novel Blockchain Oracle Network Combined With Directed Acyclic Graph Distributed Ledger 基于区块链Oracle网络和有向无环图分布式账本的高效脱链数据供给机制

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-24 DOI: 10.1109/TNSE.2025.3554239

Libo Feng;Hongyu Zhu;Bei Yu;Shaowen Yao

{"title":"Efficient Off-Chain Data Feed Mechanism Using a Novel Blockchain Oracle Network Combined With Directed Acyclic Graph Distributed Ledger","authors":"Libo Feng;Hongyu Zhu;Bei Yu;Shaowen Yao","doi":"10.1109/TNSE.2025.3554239","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554239","url":null,"abstract":"Smart contracts were introduced as autonomous programs running across a blockchain network. To solve the difficulty that smart contracts on the blockchain cannot interact with the real world, some blockchain oracle implementation schemes have been proposed. However, the existing data feed schemes still cannot meet the demand of off-chain intensive data feed. This paper introduces a directed acyclic graph (DAG)-distributed ledger into the blockchain oracle data feed scheme, to propose a DAG-distributed ledger-based decentralized oracle network (DDON) framework. The lightweight DAG consensus mechanism ensures data integrity and significantly reduces the entry of valueless information into the DDON, ultimately generating deterministic data. The proposed DAG structure enables parallel processing of transactions and accelerates the efficiency of data feeds. This also enables the feeding of historical data. In addition, an off-chain data feed mechanism is designed for off-chain intensive streaming of data feeds through the proposed oracle network, to separate data feeds from data fetches and improve the efficiency of feeding multiple requests. The evaluation results and discussions demonstrate that the proposed framework reduces the response time for every smart contract request and is more efficient and flexible than other mainstream oracle data feed services.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2810-2822"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492432","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

Joint Task Coding and Transfer Optimization for Edge Computing Power Networks 边缘计算能力网络的联合任务编码与传输优化

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-24 DOI: 10.1109/TNSE.2025.3554100

Jiajia Liu;Yunlong Lu;Hao Wu;Bo Ai;Abbas Jamalipour;Yan Zhang

{"title":"Joint Task Coding and Transfer Optimization for Edge Computing Power Networks","authors":"Jiajia Liu;Yunlong Lu;Hao Wu;Bo Ai;Abbas Jamalipour;Yan Zhang","doi":"10.1109/TNSE.2025.3554100","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3554100","url":null,"abstract":"Driven by the exponential growth of the Internet of Everything (IoE) and substantial advancements in artificial intelligence, services based on deep learning have seen a significant increase in demand for computing resources. The existing edge computing paradigms struggle to handle the explosive growth in computing demands. They also face challenges in jointly optimizing the high transmission load and privacy concerns of task collaboration while failing to utilize computing resources efficiently in complex and dynamic computing power networks. In this paper, we investigate an edge computing power network framework that integrates heterogeneous computing resources from both horizontal and vertical dimensions. We formulate a collaborative task transfer problem to minimize the total execution time of multiple tasks by joint optimization task coding, computing-task association, and collaborative transfer computing strategies among nodes. To solve the formulated problem, we conduct in-depth theoretical analyses and design a two-layer multi-agent optimization algorithm. Specifically, the task coding problem is reformulated in the inner layer into a solvable form, and a closed-form expression for the task coding ratio is derived. Subsequently, we design an adaptive hybrid reward-based multi-agent deep reinforcement learning algorithm to address the sparsity challenges of single-layer rewards while ensuring efficient and stable training convergence. Numerical results show the superiority of our proposed algorithm.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2783-2796"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144492251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Delay-Aware Robust Edge Network Hardening Under Decision-Dependent Uncertainty 决策不确定性下的延迟感知鲁棒边缘网络加固

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-21 DOI: 10.1109/TNSE.2025.3548020

Jiaming Cheng;Duong Thuy Anh Nguyen;Ni Trieu;Duong Tung Nguyen

{"title":"Delay-Aware Robust Edge Network Hardening Under Decision-Dependent Uncertainty","authors":"Jiaming Cheng;Duong Thuy Anh Nguyen;Ni Trieu;Duong Tung Nguyen","doi":"10.1109/TNSE.2025.3548020","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3548020","url":null,"abstract":"Edge computing promises to offer low-latency and ubiquitous computation to numerous devices at the network edge. For delay-sensitive applications, link delays significantly affect service quality. These delays can fluctuate substantially over time due to various factors such as network congestion, changing traffic conditions, cyberattacks, component failures, and natural disasters. Thus, it is crucial to efficiently harden the edge network to mitigate link delay variation and ensure a stable and improved user experience. To this end, we propose a novel robust model for optimal edge network hardening, considering link delay uncertainty. Unlike existing literature that treats uncertainties as exogenous, our model incorporates an endogenous uncertainty set to properly capture the impact of hardening and workload allocation decisions on link delays. However, the endogenous set introduces additional complexity to the problem due to the interdependence between decisions and uncertainties. To address this, we present two efficient methods to transform the problem into a solvable form. Extensive numerical results demonstrate the effectiveness of the proposed approach in mitigating delay variations and enhancing system performance.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 3","pages":"2388-2401"},"PeriodicalIF":6.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871101","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

DeepAW: A Customized DNN Watermarking Scheme Against Unreliable Participants DeepAW：一种针对不可靠参与者的定制DNN水印方案

IF 6.7 2区计算机科学

IEEE Transactions on Network Science and Engineering Pub Date : 2025-03-21 DOI: 10.1109/TNSE.2025.3553673

Shen Lin;Xiaoyu Zhang;Xu Ma;Xiaofeng Chen;Willy Susilo

{"title":"DeepAW: A Customized DNN Watermarking Scheme Against Unreliable Participants","authors":"Shen Lin;Xiaoyu Zhang;Xu Ma;Xiaofeng Chen;Willy Susilo","doi":"10.1109/TNSE.2025.3553673","DOIUrl":"https://doi.org/10.1109/TNSE.2025.3553673","url":null,"abstract":"Training DNNs requires large amounts of labeled data, costly computational resources, and tremendous human effort, resulting in such models being a valuable commodity. In collaborative learning scenarios, unreliable participants are widespread due to data collected from a diverse set of end-users that differ in quality and quantity. It is important to note that failure to take into account the contributions of all participants in the collaborative model training process when sharing the model with them could potentially result in a deterioration in collaborative efforts. In this paper, we propose a customized DNN watermarking scheme to safeguard the model ownership, namely <italic>DeepAW</i>, achieving robustness to model stealing attacks and collaborative fairness in the presence of unreliable participants. Specifically, <italic>DeepAW</i> leverages the tightly binding between the embedded watermarking and the model performance to defend against the model stealing attacks, resulting in the sharp decline of the model performance encountering any attempt at watermarking modification. <italic>DeepAW</i> achieves collaborative fairness by detecting unreliable participants and customizing the model performance according to the participants' contributions. Furthermore, we set up three model stealing attacks and four types of unreliable participants. The experimental results demonstrate the effectiveness, robustness, and collaborative fairness of <italic>DeepAW</i>.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"2758-2769"},"PeriodicalIF":6.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502909","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