Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitiv...Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.展开更多
The contemporary smart cities,smart homes,smart buildings,and smart health care systems are the results of the explosive growth of Internet of Things(IoT)devices and deep learning.Yet the centralized training paradigm...The contemporary smart cities,smart homes,smart buildings,and smart health care systems are the results of the explosive growth of Internet of Things(IoT)devices and deep learning.Yet the centralized training paradigms have fundamental issues in data privacy,regulatory compliance,and ownership silo alongside the scaled limitations of the real-life application.The concept of Federated Deep Learning(FDL)is a privacy-by-design method that will enable the distributed training of machine learning models among distributed clients without sharing raw data and is suitable in heterogeneous urban settings.It is an overview of the privacy-preserving developments in FDL as of 2018-2025 with a narrow scope on its usage in smart cities(traffic prediction,environmental monitoring,energy grids),smart homes/buildings/IoT(non-intrusive load monitoring,HVAC optimization,anomaly detection)and the healthcare application(medical imaging,Electronic Health Records(EHR)analysis,remote monitoring).It gives coherent taxonomy,domain pipelines,comparative analyses of privacy mechanisms(differential privacy,secure aggregation,Homomorphic Encryption(HE),Trusted Execution Environments(TEEs),blockchain enhanced and hybrids),system structures,security/robustness defense,deployment/Machine Learning Operation(MLOps)issues,and the longstanding challenges(non-IID heterogeneity,communication efficiency,fairness,and sustainability).Some of the contributions made are structured comparisons of privacy threats,practical design advice on urban areas,recognition of open problems,and a research roadmap into the future up to 2035.The paper brings out the transformational worth of FDL in building credible,scalable,and sustainable intelligent urban ecosystems and the need to do further interdisciplinary research in standardization,real-world testbeds,and ethical governance.展开更多
This study addresses the risk of privacy leakage during the transmission and sharing of multimodal data in smart grid substations by proposing a three-tier privacy-preserving architecture based on asynchronous federat...This study addresses the risk of privacy leakage during the transmission and sharing of multimodal data in smart grid substations by proposing a three-tier privacy-preserving architecture based on asynchronous federated learning.The framework integrates blockchain technology,the InterPlanetary File System(IPFS)for distributed storage,and a dynamic differential privacy mechanism to achieve collaborative security across the storage,service,and federated coordination layers.It accommodates both multimodal data classification and object detection tasks,enabling the identification and localization of key targets and abnormal behaviors in substation scenarios while ensuring privacy protection.This effectively mitigates the single-point failures and model leakage issues inherent in centralized architectures.A dynamically adjustable differential privacy mechanism is introduced to allocate privacy budgets according to client contribution levels and upload frequencies,achieving a personalized balance between model performance and privacy protection.Multi-dimensional experimental evaluations,including classification accuracy,F1-score,encryption latency,and aggregation latency,verify the security and efficiency of the proposed architecture.The improved CNN model achieves 72.34%accuracy and an F1-score of 0.72 in object detection and classification tasks on infrared surveillance imagery,effectively identifying typical risk events such as not wearing safety helmets and unauthorized intrusion,while maintaining an aggregation latency of only 1.58 s and a query latency of 80.79 ms.Compared with traditional static differential privacy and centralized approaches,the proposed method demonstrates significant advantages in accuracy,latency,and security,providing a new technical paradigm for efficient,secure data sharing,object detection,and privacy preservation in smart grid substations.展开更多
Multimodal spatiotemporal data from smart city consumer electronics present critical challenges including cross-modal temporal misalignment,unreliable data quality,limited joint modeling of spatial and temporal depend...Multimodal spatiotemporal data from smart city consumer electronics present critical challenges including cross-modal temporal misalignment,unreliable data quality,limited joint modeling of spatial and temporal dependencies,and weak resilience to adversarial updates.To address these limitations,EdgeST-Fusion is introduced as a cross-modal federated graph transformer framework for context-aware smart city analytics.The architecture integrates cross-modal embedding networks for modality alignment,graph transformer encoders for spatial dependency modeling,temporal self-attention for dynamic pattern learning,and adaptive anomaly detection to ensure data quality and security during aggregation.A privacy-preserving federated learning protocol with differential privacy guarantees enables collaborative model training without centralizing sensitive data.The framework employs data-quality-aware weighted aggregation to enhance robustness against noisy and malicious client updates.Experimental evaluation on the GeoLife,PeMS-Bay,and SmartHome+datasets demonstrates that EdgeST-Fusion achieves 21.8%improvement in prediction accuracy,35.7%reduction in communication overhead,and 29.4%enhancement in security resilience compared to recent baselines.Real-world deployment across three smart city testbeds validates practical viability with 90.0%average accuracy and sub-250 ms inference latency.The proposed framework remains feasible for deployment on heterogeneous and resource-constrained consumer electronics devices whilemaintaining strong privacy guarantees and scalability for large-scale urban environments.展开更多
In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mec...In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.展开更多
With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy...With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy.However,efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging.To address these issues,we propose Federated Learning with Client Selection and Adaptive Weighting(FedCW),a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks.FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts aggregation weights to optimize both data diversity and model convergence.Experimental results show that FedCW significantly outperforms existing FL algorithms such as FedAvg,FedProx,and SCAFFOLD,particularly in non-IID settings,achieving faster convergence,higher accuracy,and reduced communication overhead.These findings demonstrate that FedCW provides an effective solution for enhancing the performance of FL in heterogeneous,edge-based computing environments.展开更多
The Internet of Vehicles,or IoV,is expected to lessen pollution,ease traffic,and increase road safety.IoV entities’interconnectedness,however,raises the possibility of cyberattacks,which can have detrimental effects....The Internet of Vehicles,or IoV,is expected to lessen pollution,ease traffic,and increase road safety.IoV entities’interconnectedness,however,raises the possibility of cyberattacks,which can have detrimental effects.IoV systems typically send massive volumes of raw data to central servers,which may raise privacy issues.Additionally,model training on IoV devices with limited resources normally leads to slower training times and reduced service quality.We discuss a privacy-preserving Federated Split Learning with Tiny Machine Learning(TinyML)approach,which operates on IoV edge devices without sharing sensitive raw data.Specifically,we focus on integrating split learning(SL)with federated learning(FL)and TinyML models.FL is a decentralisedmachine learning(ML)technique that enables numerous edge devices to train a standard model while retaining data locally collectively.The article intends to thoroughly discuss the architecture and challenges associated with the increasing prevalence of SL in the IoV domain,coupled with FL and TinyML.The approach starts with the IoV learning framework,which includes edge computing,FL,SL,and TinyML,and then proceeds to discuss how these technologies might be integrated.We elucidate the comprehensive operational principles of Federated and split learning by examining and addressingmany challenges.We subsequently examine the integration of SL with FL and various applications of TinyML.Finally,exploring the potential integration of FL and SL with TinyML in the IoV domain is referred to as FSL-TM.It is a superior method for preserving privacy as it conducts model training on individual devices or edge nodes,thereby obviating the necessity for centralised data aggregation,which presents considerable privacy threats.The insights provided aim to help both researchers and practitioners understand the complicated terrain of FL and SL,hence facilitating advancement in this swiftly progressing domain.展开更多
Keratitis is a common ophthalmic disease associated with a high risk of blindness.Although deep learning(DL) based on slit-lamp images has shown great promise for automatic keratitis diagnosis,data heterogeneity and p...Keratitis is a common ophthalmic disease associated with a high risk of blindness.Although deep learning(DL) based on slit-lamp images has shown great promise for automatic keratitis diagnosis,data heterogeneity and privacy constraints hinder data sharing,limiting model generalization across multiple medical centers.To address these challenges,we propose a similarity-guided dynamic adjustment federated learning algorithm for automated keratitis diagnosis(SDAFL_AKD).SDAFL_AKD introduces a similarity-based regularization term during local model updates to alleviate catastrophic forgetting and employs a performance-driven dynamic aggregation mechanism on the server-side to adaptively weight client contributions,thereby enhancing global model robustness under non-independent and identically distributed(Non-IID) conditions.The framework is evaluated on slit-lamp images collected from four independent data sources encompassing keratitis,normal cornea,and other cornea abnormalities,and compared with Fed Avg,model-contrastive federated learning(MOON),stochastic controlled averaging for federated learning(SCAFFOLD) and single-center baseline models.Experimental results demonstrate that SDAFL_AKD consistently outperforms conventional methods,achieving average accuracies of 97.95% on a balanced dataset and 86.05% on an imbalanced smart phone-acquired dataset.Ablation studies further confirm the synergistic benefits of the similarity(SIM) and dynamic aggregation(DA) modules in improving multi-category recognition and generalization.These findings indicate the effectiveness of SDAFL_AKD for keratitis diagnosis under data heterogeneous and privacy-constrained conditions,providing a scalable solution for collaborative ophthalmic image analysis across institutions.展开更多
With the increasing complexity of malware attack techniques,traditional detection methods face significant challenges,such as privacy preservation,data heterogeneity,and lacking category information.To address these i...With the increasing complexity of malware attack techniques,traditional detection methods face significant challenges,such as privacy preservation,data heterogeneity,and lacking category information.To address these issues,we propose Federated Dynamic Prototype Learning(FedDPL)for malware classification by integrating Federated Learning with a specifically designed K-means.Under the Federated Learning framework,model training occurs locally without data sharing,effectively protecting user data privacy and preventing the leakage of sensitive information.Furthermore,to tackle the challenges of data heterogeneity and the lack of category information,FedDPL introduces a dynamic prototype learning mechanism,which adaptively adjusts the clustering prototypes in terms of position and number.Thus,the dependency on predefined category numbers in typical K-means and its variants can be significantly reduced,resulting in improved clustering performance.Theoretically,it provides a more accurate detection of malicious behavior.Experimental results confirm that FedDPL excels in handling malware classification tasks,demonstrating superior accuracy,robustness,and privacy protection.展开更多
Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work pr...Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work proposes Secured-FL,a blockchain-based defensive framework that combines smart contract-based authentication,clustering-driven outlier elimination,and dynamic threshold adjustment to defend against adversarial attacks.The framework was implemented on a private Ethereum network with a Proof-of-Authority consensus algorithm to ensure tamper-resistant and auditable model updates.Large-scale simulation on the Cyber Data dataset,under up to 50%malicious client settings,demonstrates Secured-FL achieves 6%-12%higher accuracy,9%-15%lower latency,and approximately 14%less computational expense compared to the PPSS benchmark framework.Additional tests,including confusion matrices,ROC and Precision-Recall curves,and ablation tests,confirm the interpretability and robustness of the defense.Tests for scalability also show consistent performance up to 500 clients,affirming appropriateness to reasonably large deployments.These results make Secured-FL a feasible,adversarially resilient FL paradigm with promising potential for application in smart cities,medicine,and other mission-critical IoT deployments.展开更多
The growing developments in 5G and 6G wireless communications have revolutionized communications technologies,providing faster speeds with reduced latency and improved connectivity to users.However,it raises significa...The growing developments in 5G and 6G wireless communications have revolutionized communications technologies,providing faster speeds with reduced latency and improved connectivity to users.However,it raises significant security challenges,including impersonation threats,data manipulation,distributed denial of service(DDoS)attacks,and privacy breaches.Traditional security measures are inadequate due to the decentralized and dynamic nature of next-generation networks.This survey provides a comprehensive review of how Federated Learning(FL),Blockchain,and Digital Twin(DT)technologies can collectively enhance the security of 5G and 6G systems.Blockchain offers decentralized,immutable,and transparent mechanisms for securing network transactions,while FL enables privacy-preserving collaborative learning without sharing raw data.Digital Twins create virtual replicas of network components,enabling real-time monitoring,anomaly detection,and predictive threat analysis.The survey examines major security issues in emerging wireless architectures and analyzes recent advancements that integrate FL,Blockchain,and DT to mitigate these threats.Additionally,it presents practical use cases,synthesizes key lessons learned,and identifies ongoing research challenges.Finally,the survey outlines future research directions to support the development of scalable,intelligent,and robust security frameworks for next-generation wireless networks.展开更多
The technological advancement of the vehicular Internet ofThings(IoT)has revolutionized Intelligent Transportation Systems(ITS)into next-generation ITS.The connectivity of IoT nodes enables improved data availability ...The technological advancement of the vehicular Internet ofThings(IoT)has revolutionized Intelligent Transportation Systems(ITS)into next-generation ITS.The connectivity of IoT nodes enables improved data availability and facilitates automatic control in the ITS environment.The exponential increase in IoT nodes has significantly increased the demand for an energy-efficient,mobility-aware,and secure system for distributed intelligence.This article presents a mobility-aware Deep Reinforcement Learning based Federated Learning(DRL-FL)approach to design an energy-efficient and threat-resilient ITS.In this approach,a Policy Proximal Optimization(PPO)-based DRL agent is first employed for adaptive client selection.Second,an autoencoder-based anomaly detectionmodule is considered for malicious node detection.Results reveal that the proposed framework achieved an 8%higher accuracy increase,and 15%lower energy consumption.Themodel also demonstrates greater resilience under adversarial conditions compared to the state of the art in federated learning.The adaptability of the proposed approach makes it a compelling choice for next-generation vehicular networks.展开更多
Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,exi...Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.展开更多
The increasing number of interconnected devices and the incorporation of smart technology into contemporary healthcare systems have significantly raised the attack surface of cyber threats.The early detection of threa...The increasing number of interconnected devices and the incorporation of smart technology into contemporary healthcare systems have significantly raised the attack surface of cyber threats.The early detection of threats is both necessary and complex,yet these interconnected healthcare settings generate enormous amounts of heterogeneous data.Traditional Intrusion Detection Systems(IDS),which are generally centralized and machine learning-based,often fail to address the rapidly changing nature of cyberattacks and are challenged by ethical concerns related to patient data privacy.Moreover,traditional AI-driven IDS usually face challenges in handling large-scale,heterogeneous healthcare data while ensuring data privacy and operational efficiency.To address these issues,emerging technologies such as Big Data Analytics(BDA)and Federated Learning(FL)provide a hybrid framework for scalable,adaptive intrusion detection in IoT-driven healthcare systems.Big data techniques enable processing large-scale,highdimensional healthcare data,and FL can be used to train a model in a decentralized manner without transferring raw data,thereby maintaining privacy between institutions.This research proposes a privacy-preserving Federated Learning–based model that efficiently detects cyber threats in connected healthcare systems while ensuring distributed big data processing,privacy,and compliance with ethical regulations.To strengthen the reliability of the reported findings,the resultswere validated using cross-dataset testing and 95%confidence intervals derived frombootstrap analysis,confirming consistent performance across heterogeneous healthcare data distributions.This solution takes a significant step toward securing next-generation healthcare infrastructure by combining scalability,privacy,adaptability,and earlydetection capabilities.The proposed global model achieves a test accuracy of 99.93%±0.03(95%CI)and amiss-rate of only 0.07%±0.02,representing state-of-the-art performance in privacy-preserving intrusion detection.The proposed FL-driven IDS framework offers an efficient,privacy-preserving,and scalable solution for securing next-generation healthcare infrastructures by combining adaptability,early detection,and ethical data management.展开更多
Multi-label feature selection(MFS)is a crucial dimensionality reduction technique aimed at identifying informative features associated with multiple labels.However,traditional centralized methods face significant chal...Multi-label feature selection(MFS)is a crucial dimensionality reduction technique aimed at identifying informative features associated with multiple labels.However,traditional centralized methods face significant challenges in privacy-sensitive and distributed settings,often neglecting label dependencies and suffering from low computational efficiency.To address these issues,we introduce a novel framework,Fed-MFSDHBCPSO—federated MFS via dual-layer hybrid breeding cooperative particle swarm optimization algorithm with manifold and sparsity regularization(DHBCPSO-MSR).Leveraging the federated learning paradigm,Fed-MFSDHBCPSO allows clients to perform local feature selection(FS)using DHBCPSO-MSR.Locally selected feature subsets are encrypted with differential privacy(DP)and transmitted to a central server,where they are securely aggregated and refined through secure multi-party computation(SMPC)until global convergence is achieved.Within each client,DHBCPSO-MSR employs a dual-layer FS strategy.The inner layer constructs sample and label similarity graphs,generates Laplacian matrices to capture the manifold structure between samples and labels,and applies L2,1-norm regularization to sparsify the feature subset,yielding an optimized feature weight matrix.The outer layer uses a hybrid breeding cooperative particle swarm optimization algorithm to further refine the feature weight matrix and identify the optimal feature subset.The updated weight matrix is then fed back to the inner layer for further optimization.Comprehensive experiments on multiple real-world multi-label datasets demonstrate that Fed-MFSDHBCPSO consistently outperforms both centralized and federated baseline methods across several key evaluation metrics.展开更多
Federated learning often experiences slow and unstable convergence due to edge-side data heterogeneity.This problem becomes more severe when edge participation rate is low,as the information collected from different e...Federated learning often experiences slow and unstable convergence due to edge-side data heterogeneity.This problem becomes more severe when edge participation rate is low,as the information collected from different edge devices varies significantly.As a result,communication overhead increases,which further slows down the convergence process.To address this challenge,we propose a simple yet effective federated learning framework that improves consistency among edge devices.The core idea is clusters the lookahead gradients collected from edge devices on the cloud server to obtain personalized momentum for steering local updates.In parallel,a global momentum is applied during model aggregation,enabling faster convergence while preserving personalization.This strategy enables efficient propagation of the estimated global update direction to all participating edge devices and maintains alignment in local training,without introducing extra memory or communication overhead.We conduct extensive experiments on benchmark datasets such as Cifar100 and Tiny-ImageNet.The results confirm the effectiveness of our framework.On CIFAR-100,our method reaches 55%accuracy with 37 fewer rounds and achieves a competitive final accuracy of 65.46%.Even under extreme non-IID scenarios,it delivers significant improvements in both accuracy and communication efficiency.The implementation is publicly available at https://github.com/sjmp525/CollaborativeComputing/tree/FedCCM(accessed on 20 October 2025).展开更多
Federated Learning(FL)protects data privacy through a distributed training mechanism,yet its decentralized nature also introduces new security vulnerabilities.Backdoor attacks inject malicious triggers into the global...Federated Learning(FL)protects data privacy through a distributed training mechanism,yet its decentralized nature also introduces new security vulnerabilities.Backdoor attacks inject malicious triggers into the global model through compromised updates,posing significant threats to model integrity and becoming a key focus in FL security.Existing backdoor attack methods typically embed triggers directly into original images and consider only data heterogeneity,resulting in limited stealth and adaptability.To address the heterogeneity of malicious client devices,this paper proposes a novel backdoor attack method named Capability-Adaptive Shadow Backdoor Attack(CASBA).By incorporating measurements of clients’computational and communication capabilities,CASBA employs a dynamic hierarchical attack strategy that adaptively aligns attack intensity with available resources.Furthermore,an improved deep convolutional generative adversarial network(DCGAN)is integrated into the attack pipeline to embed triggers without modifying original data,significantly enhancing stealthiness.Comparative experiments with Shadow Backdoor Attack(SBA)across multiple scenarios demonstrate that CASBA dynamically adjusts resource consumption based on device capabilities,reducing average memory usage per iteration by 5.8%.CASBA improves resource efficiency while keeping the drop in attack success rate within 3%.Additionally,the effectiveness of CASBA against three robust FL algorithms is also validated.展开更多
ABSTRACT:Federated Learning(FL)enables collaborative medical model training without sharing sensitive patient data.However,existing FL systems face increasing security risks from post quantum adversaries and often inc...ABSTRACT:Federated Learning(FL)enables collaborative medical model training without sharing sensitive patient data.However,existing FL systems face increasing security risks from post quantum adversaries and often incur nonnegligible computational and communication overhead when encryption is applied.At the same time,training high performance AI models requires large volumes of high quality data,while medical data such as patient information,clinical records,and diagnostic reports are highly sensitive and subject to strict privacy regulations,including HIPAA and GDPR.Traditional centralized machine learning approaches therefore pose significant challenges for cross institutional collaboration in healthcare.To address these limitations,Federated Learning was introduced to allow multiple institutions to jointly train a global model while keeping local data private.Nevertheless,conventional cryptographicmechanisms,such as RSA,are increasingly inadequate for privacy sensitive FL deployments,particularly in the presence of emerging quantum computing threats.Homomorphic encryption,which enables computations to be performed directly on encrypted data,provides an effective solution for preserving data privacy in federated learning systems.This capability allows healthcare institutions to securely perform collaborative model training while remaining compliant with regulatory requirements.Among homomorphic encryption techniques,NTRU,a lattice based cryptographic scheme defined over polynomial rings,offers strong resistance against quantum attacks by relying on the hardness of the Shortest Vector Problem(SVP).Moreover,NTRU supports limited homomorphic operations that are sufficient for secure aggregation in federated learning.In this work,we propose an NTRU enhanced federated learning framework specifically designed for medical and healthcare applications.Experimental results demonstrate that the proposed approach achieves classification performance comparable to standard federated learning,with final accuracy consistently exceeding 0.93.The framework introduces predictable encryption latency on the order of hundreds of milliseconds per training round and a fixed ciphertext communication overhead per client under practical deployment settings.In addition,the proposed systemeffectivelymitigatesmultiple security threats,including quantum computing attacks,by ensuring robust encryption throughout the training process.By integrating the security and homomorphic properties of NTRU,this study establishes a privacy preserving and quantumresistant federated learning framework that supports the secure,legal,and efficient deployment of AI technologies in healthcare,thereby laying a solid foundation for future intelligent healthcare systems.展开更多
Nowadays,advances in communication technology and cloud computing have spawned a variety of smart mobile devices,which will generate a great amount of computing-intensive businesses,and require corresponding resources...Nowadays,advances in communication technology and cloud computing have spawned a variety of smart mobile devices,which will generate a great amount of computing-intensive businesses,and require corresponding resources of computation and communication.Multiaccess edge computing(MEC)can offload computing-intensive tasks to the nearby edge servers,which alleviates the pressure of devices.Ultra-dense network(UDN)can provide effective spectrum resources by deploying a large number of micro base stations.Furthermore,network slicing can support various applications in different communication scenarios.Therefore,this paper integrates the ultra-dense network slicing and the MEC technology,and introduces a hybrid computing offloading strategy in order to satisfy various quality of service(QoS)of edge devices.In order to dynamically allocate limited resources,the above problem is formulated as multiagent distributed deep reinforcement learning(DRL),which will achieve low overhead computation offloading strategy and real-time resource allocation decisions.In this context,federated learning is added to train DRL agents in a distributed manner,where each agent is dedicated to exploring actions composed of offloading decisions and allocating resources,so as to jointly optimize system delay and energy consumption.Simulation results show that the proposed learning algorithm has better performance compared with other strategies in literature.展开更多
文摘Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.
文摘The contemporary smart cities,smart homes,smart buildings,and smart health care systems are the results of the explosive growth of Internet of Things(IoT)devices and deep learning.Yet the centralized training paradigms have fundamental issues in data privacy,regulatory compliance,and ownership silo alongside the scaled limitations of the real-life application.The concept of Federated Deep Learning(FDL)is a privacy-by-design method that will enable the distributed training of machine learning models among distributed clients without sharing raw data and is suitable in heterogeneous urban settings.It is an overview of the privacy-preserving developments in FDL as of 2018-2025 with a narrow scope on its usage in smart cities(traffic prediction,environmental monitoring,energy grids),smart homes/buildings/IoT(non-intrusive load monitoring,HVAC optimization,anomaly detection)and the healthcare application(medical imaging,Electronic Health Records(EHR)analysis,remote monitoring).It gives coherent taxonomy,domain pipelines,comparative analyses of privacy mechanisms(differential privacy,secure aggregation,Homomorphic Encryption(HE),Trusted Execution Environments(TEEs),blockchain enhanced and hybrids),system structures,security/robustness defense,deployment/Machine Learning Operation(MLOps)issues,and the longstanding challenges(non-IID heterogeneity,communication efficiency,fairness,and sustainability).Some of the contributions made are structured comparisons of privacy threats,practical design advice on urban areas,recognition of open problems,and a research roadmap into the future up to 2035.The paper brings out the transformational worth of FDL in building credible,scalable,and sustainable intelligent urban ecosystems and the need to do further interdisciplinary research in standardization,real-world testbeds,and ethical governance.
基金funded by the National Natural Science Foundation of China,grant number 61605004the Fundamental Research Funds for the Central Universities,grant number FRF-TP-19-016A2Guizhou Power Grid Co.,Ltd.2024 first batch of services(2024-2026 technology R&D services for science and technology projects(in addition to national and SGCC key projects)),grant number 060100KC23100012。
文摘This study addresses the risk of privacy leakage during the transmission and sharing of multimodal data in smart grid substations by proposing a three-tier privacy-preserving architecture based on asynchronous federated learning.The framework integrates blockchain technology,the InterPlanetary File System(IPFS)for distributed storage,and a dynamic differential privacy mechanism to achieve collaborative security across the storage,service,and federated coordination layers.It accommodates both multimodal data classification and object detection tasks,enabling the identification and localization of key targets and abnormal behaviors in substation scenarios while ensuring privacy protection.This effectively mitigates the single-point failures and model leakage issues inherent in centralized architectures.A dynamically adjustable differential privacy mechanism is introduced to allocate privacy budgets according to client contribution levels and upload frequencies,achieving a personalized balance between model performance and privacy protection.Multi-dimensional experimental evaluations,including classification accuracy,F1-score,encryption latency,and aggregation latency,verify the security and efficiency of the proposed architecture.The improved CNN model achieves 72.34%accuracy and an F1-score of 0.72 in object detection and classification tasks on infrared surveillance imagery,effectively identifying typical risk events such as not wearing safety helmets and unauthorized intrusion,while maintaining an aggregation latency of only 1.58 s and a query latency of 80.79 ms.Compared with traditional static differential privacy and centralized approaches,the proposed method demonstrates significant advantages in accuracy,latency,and security,providing a new technical paradigm for efficient,secure data sharing,object detection,and privacy preservation in smart grid substations.
基金supported by the University of Tabuk,Saudi Arabia。
文摘Multimodal spatiotemporal data from smart city consumer electronics present critical challenges including cross-modal temporal misalignment,unreliable data quality,limited joint modeling of spatial and temporal dependencies,and weak resilience to adversarial updates.To address these limitations,EdgeST-Fusion is introduced as a cross-modal federated graph transformer framework for context-aware smart city analytics.The architecture integrates cross-modal embedding networks for modality alignment,graph transformer encoders for spatial dependency modeling,temporal self-attention for dynamic pattern learning,and adaptive anomaly detection to ensure data quality and security during aggregation.A privacy-preserving federated learning protocol with differential privacy guarantees enables collaborative model training without centralizing sensitive data.The framework employs data-quality-aware weighted aggregation to enhance robustness against noisy and malicious client updates.Experimental evaluation on the GeoLife,PeMS-Bay,and SmartHome+datasets demonstrates that EdgeST-Fusion achieves 21.8%improvement in prediction accuracy,35.7%reduction in communication overhead,and 29.4%enhancement in security resilience compared to recent baselines.Real-world deployment across three smart city testbeds validates practical viability with 90.0%average accuracy and sub-250 ms inference latency.The proposed framework remains feasible for deployment on heterogeneous and resource-constrained consumer electronics devices whilemaintaining strong privacy guarantees and scalability for large-scale urban environments.
文摘In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.
文摘With the increasing complexity of vehicular networks and the proliferation of connected vehicles,Federated Learning(FL)has emerged as a critical framework for decentralized model training while preserving data privacy.However,efficient client selection and adaptive weight allocation in heterogeneous and non-IID environments remain challenging.To address these issues,we propose Federated Learning with Client Selection and Adaptive Weighting(FedCW),a novel algorithm that leverages adaptive client selection and dynamic weight allocation for optimizing model convergence in real-time vehicular networks.FedCW selects clients based on their Euclidean distance from the global model and dynamically adjusts aggregation weights to optimize both data diversity and model convergence.Experimental results show that FedCW significantly outperforms existing FL algorithms such as FedAvg,FedProx,and SCAFFOLD,particularly in non-IID settings,achieving faster convergence,higher accuracy,and reduced communication overhead.These findings demonstrate that FedCW provides an effective solution for enhancing the performance of FL in heterogeneous,edge-based computing environments.
文摘The Internet of Vehicles,or IoV,is expected to lessen pollution,ease traffic,and increase road safety.IoV entities’interconnectedness,however,raises the possibility of cyberattacks,which can have detrimental effects.IoV systems typically send massive volumes of raw data to central servers,which may raise privacy issues.Additionally,model training on IoV devices with limited resources normally leads to slower training times and reduced service quality.We discuss a privacy-preserving Federated Split Learning with Tiny Machine Learning(TinyML)approach,which operates on IoV edge devices without sharing sensitive raw data.Specifically,we focus on integrating split learning(SL)with federated learning(FL)and TinyML models.FL is a decentralisedmachine learning(ML)technique that enables numerous edge devices to train a standard model while retaining data locally collectively.The article intends to thoroughly discuss the architecture and challenges associated with the increasing prevalence of SL in the IoV domain,coupled with FL and TinyML.The approach starts with the IoV learning framework,which includes edge computing,FL,SL,and TinyML,and then proceeds to discuss how these technologies might be integrated.We elucidate the comprehensive operational principles of Federated and split learning by examining and addressingmany challenges.We subsequently examine the integration of SL with FL and various applications of TinyML.Finally,exploring the potential integration of FL and SL with TinyML in the IoV domain is referred to as FSL-TM.It is a superior method for preserving privacy as it conducts model training on individual devices or edge nodes,thereby obviating the necessity for centralised data aggregation,which presents considerable privacy threats.The insights provided aim to help both researchers and practitioners understand the complicated terrain of FL and SL,hence facilitating advancement in this swiftly progressing domain.
基金Supported by the National Natural Science Foundation of China (No.62276210,82201148,62376215)the Key Research and Development Project of Shaanxi Province (No.2025CY-YBXM-044,2024GX-YBXM-137)+5 种基金the Ningbo Top Medical and Health Research Program (No.2023030716)the Natural Science Foundation of Ningbo (No.2023J390)Interdisciplinary Research Program of the School of Electronic Engineering,Xi’an University of Posts and Telecommunications (No.XKJC2501)the Open Fund of National Engineering Laboratory for Big Data System Computing Technology (No.SZU-BDSC-OF2024-16)the Key Research and Development Project of Xianyang (No.L2024-ZDYF-ZDYF-SF-0067)General Special Scientific Research Program of Shaanxi Provincial Department of Education (No.24JK0651)。
文摘Keratitis is a common ophthalmic disease associated with a high risk of blindness.Although deep learning(DL) based on slit-lamp images has shown great promise for automatic keratitis diagnosis,data heterogeneity and privacy constraints hinder data sharing,limiting model generalization across multiple medical centers.To address these challenges,we propose a similarity-guided dynamic adjustment federated learning algorithm for automated keratitis diagnosis(SDAFL_AKD).SDAFL_AKD introduces a similarity-based regularization term during local model updates to alleviate catastrophic forgetting and employs a performance-driven dynamic aggregation mechanism on the server-side to adaptively weight client contributions,thereby enhancing global model robustness under non-independent and identically distributed(Non-IID) conditions.The framework is evaluated on slit-lamp images collected from four independent data sources encompassing keratitis,normal cornea,and other cornea abnormalities,and compared with Fed Avg,model-contrastive federated learning(MOON),stochastic controlled averaging for federated learning(SCAFFOLD) and single-center baseline models.Experimental results demonstrate that SDAFL_AKD consistently outperforms conventional methods,achieving average accuracies of 97.95% on a balanced dataset and 86.05% on an imbalanced smart phone-acquired dataset.Ablation studies further confirm the synergistic benefits of the similarity(SIM) and dynamic aggregation(DA) modules in improving multi-category recognition and generalization.These findings indicate the effectiveness of SDAFL_AKD for keratitis diagnosis under data heterogeneous and privacy-constrained conditions,providing a scalable solution for collaborative ophthalmic image analysis across institutions.
基金supported by the National Natural Science Foundation of China under Grant No.62162009the Key Technologies R&D Program of He’nan Province under Grant No.242102211065+2 种基金the Postgraduate Education Reform and Quality Improvement Project of Henan Province under Grant Nos.YJS2025GZZ36,YJS2024AL112,and YJS2024JD38the Innovation Scientists and Technicians Troop Construction Projects of Henan Province under Grant No.CXTD2017099the Scientific Research Innovation Team of Xuchang University under Grant No.2022CXTD003.
文摘With the increasing complexity of malware attack techniques,traditional detection methods face significant challenges,such as privacy preservation,data heterogeneity,and lacking category information.To address these issues,we propose Federated Dynamic Prototype Learning(FedDPL)for malware classification by integrating Federated Learning with a specifically designed K-means.Under the Federated Learning framework,model training occurs locally without data sharing,effectively protecting user data privacy and preventing the leakage of sensitive information.Furthermore,to tackle the challenges of data heterogeneity and the lack of category information,FedDPL introduces a dynamic prototype learning mechanism,which adaptively adjusts the clustering prototypes in terms of position and number.Thus,the dependency on predefined category numbers in typical K-means and its variants can be significantly reduced,resulting in improved clustering performance.Theoretically,it provides a more accurate detection of malicious behavior.Experimental results confirm that FedDPL excels in handling malware classification tasks,demonstrating superior accuracy,robustness,and privacy protection.
文摘Federated Learning(FL)enables joint training over distributed devices without data exchange but is highly vulnerable to attacks by adversaries in the form of model poisoning and malicious update injection.This work proposes Secured-FL,a blockchain-based defensive framework that combines smart contract-based authentication,clustering-driven outlier elimination,and dynamic threshold adjustment to defend against adversarial attacks.The framework was implemented on a private Ethereum network with a Proof-of-Authority consensus algorithm to ensure tamper-resistant and auditable model updates.Large-scale simulation on the Cyber Data dataset,under up to 50%malicious client settings,demonstrates Secured-FL achieves 6%-12%higher accuracy,9%-15%lower latency,and approximately 14%less computational expense compared to the PPSS benchmark framework.Additional tests,including confusion matrices,ROC and Precision-Recall curves,and ablation tests,confirm the interpretability and robustness of the defense.Tests for scalability also show consistent performance up to 500 clients,affirming appropriateness to reasonably large deployments.These results make Secured-FL a feasible,adversarially resilient FL paradigm with promising potential for application in smart cities,medicine,and other mission-critical IoT deployments.
基金derived from a research grant“Cybersecurity Research and Innovation Pioneers Grants Initiative”funded by The National Program for RDI in Cybersecurity(National Cybersecurity Authority)-Kingdom of Saudi Arabia-with grant number(CRPG-25-3168)supported by EIAS Data Science and Blockchain Lab,CCIS,Prince Sultan University.
文摘The growing developments in 5G and 6G wireless communications have revolutionized communications technologies,providing faster speeds with reduced latency and improved connectivity to users.However,it raises significant security challenges,including impersonation threats,data manipulation,distributed denial of service(DDoS)attacks,and privacy breaches.Traditional security measures are inadequate due to the decentralized and dynamic nature of next-generation networks.This survey provides a comprehensive review of how Federated Learning(FL),Blockchain,and Digital Twin(DT)technologies can collectively enhance the security of 5G and 6G systems.Blockchain offers decentralized,immutable,and transparent mechanisms for securing network transactions,while FL enables privacy-preserving collaborative learning without sharing raw data.Digital Twins create virtual replicas of network components,enabling real-time monitoring,anomaly detection,and predictive threat analysis.The survey examines major security issues in emerging wireless architectures and analyzes recent advancements that integrate FL,Blockchain,and DT to mitigate these threats.Additionally,it presents practical use cases,synthesizes key lessons learned,and identifies ongoing research challenges.Finally,the survey outlines future research directions to support the development of scalable,intelligent,and robust security frameworks for next-generation wireless networks.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project No.PNURSP2025R510Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The technological advancement of the vehicular Internet ofThings(IoT)has revolutionized Intelligent Transportation Systems(ITS)into next-generation ITS.The connectivity of IoT nodes enables improved data availability and facilitates automatic control in the ITS environment.The exponential increase in IoT nodes has significantly increased the demand for an energy-efficient,mobility-aware,and secure system for distributed intelligence.This article presents a mobility-aware Deep Reinforcement Learning based Federated Learning(DRL-FL)approach to design an energy-efficient and threat-resilient ITS.In this approach,a Policy Proximal Optimization(PPO)-based DRL agent is first employed for adaptive client selection.Second,an autoencoder-based anomaly detectionmodule is considered for malicious node detection.Results reveal that the proposed framework achieved an 8%higher accuracy increase,and 15%lower energy consumption.Themodel also demonstrates greater resilience under adversarial conditions compared to the state of the art in federated learning.The adaptability of the proposed approach makes it a compelling choice for next-generation vehicular networks.
基金supported by National Natural Science Foundation of China(62466045)Inner Mongolia Natural Science Foundation Project(2021LHMS06003)Inner Mongolia University Basic Research Business Fee Project(114).
文摘Graph Federated Learning(GFL)has shown great potential in privacy protection and distributed intelligence through distributed collaborative training of graph-structured data without sharing raw information.However,existing GFL approaches often lack the capability for comprehensive feature extraction and adaptive optimization,particularly in non-independent and identically distributed(NON-IID)scenarios where balancing global structural understanding and local node-level detail remains a challenge.To this end,this paper proposes a novel framework called GFL-SAR(Graph Federated Collaborative Learning Framework Based on Structural Amplification and Attention Refinement),which enhances the representation learning capability of graph data through a dual-branch collaborative design.Specifically,we propose the Structural Insight Amplifier(SIA),which utilizes an improved Graph Convolutional Network(GCN)to strengthen structural awareness and improve modeling of topological patterns.In parallel,we propose the Attentive Relational Refiner(ARR),which employs an enhanced Graph Attention Network(GAT)to perform fine-grained modeling of node relationships and neighborhood features,thereby improving the expressiveness of local interactions and preserving critical contextual information.GFL-SAR effectively integrates multi-scale features from every branch via feature fusion and federated optimization,thereby addressing existing GFL limitations in structural modeling and feature representation.Experiments on standard benchmark datasets including Cora,Citeseer,Polblogs,and Cora_ML demonstrate that GFL-SAR achieves superior performance in classification accuracy,convergence speed,and robustness compared to existing methods,confirming its effectiveness and generalizability in GFL tasks.
文摘The increasing number of interconnected devices and the incorporation of smart technology into contemporary healthcare systems have significantly raised the attack surface of cyber threats.The early detection of threats is both necessary and complex,yet these interconnected healthcare settings generate enormous amounts of heterogeneous data.Traditional Intrusion Detection Systems(IDS),which are generally centralized and machine learning-based,often fail to address the rapidly changing nature of cyberattacks and are challenged by ethical concerns related to patient data privacy.Moreover,traditional AI-driven IDS usually face challenges in handling large-scale,heterogeneous healthcare data while ensuring data privacy and operational efficiency.To address these issues,emerging technologies such as Big Data Analytics(BDA)and Federated Learning(FL)provide a hybrid framework for scalable,adaptive intrusion detection in IoT-driven healthcare systems.Big data techniques enable processing large-scale,highdimensional healthcare data,and FL can be used to train a model in a decentralized manner without transferring raw data,thereby maintaining privacy between institutions.This research proposes a privacy-preserving Federated Learning–based model that efficiently detects cyber threats in connected healthcare systems while ensuring distributed big data processing,privacy,and compliance with ethical regulations.To strengthen the reliability of the reported findings,the resultswere validated using cross-dataset testing and 95%confidence intervals derived frombootstrap analysis,confirming consistent performance across heterogeneous healthcare data distributions.This solution takes a significant step toward securing next-generation healthcare infrastructure by combining scalability,privacy,adaptability,and earlydetection capabilities.The proposed global model achieves a test accuracy of 99.93%±0.03(95%CI)and amiss-rate of only 0.07%±0.02,representing state-of-the-art performance in privacy-preserving intrusion detection.The proposed FL-driven IDS framework offers an efficient,privacy-preserving,and scalable solution for securing next-generation healthcare infrastructures by combining adaptability,early detection,and ethical data management.
文摘Multi-label feature selection(MFS)is a crucial dimensionality reduction technique aimed at identifying informative features associated with multiple labels.However,traditional centralized methods face significant challenges in privacy-sensitive and distributed settings,often neglecting label dependencies and suffering from low computational efficiency.To address these issues,we introduce a novel framework,Fed-MFSDHBCPSO—federated MFS via dual-layer hybrid breeding cooperative particle swarm optimization algorithm with manifold and sparsity regularization(DHBCPSO-MSR).Leveraging the federated learning paradigm,Fed-MFSDHBCPSO allows clients to perform local feature selection(FS)using DHBCPSO-MSR.Locally selected feature subsets are encrypted with differential privacy(DP)and transmitted to a central server,where they are securely aggregated and refined through secure multi-party computation(SMPC)until global convergence is achieved.Within each client,DHBCPSO-MSR employs a dual-layer FS strategy.The inner layer constructs sample and label similarity graphs,generates Laplacian matrices to capture the manifold structure between samples and labels,and applies L2,1-norm regularization to sparsify the feature subset,yielding an optimized feature weight matrix.The outer layer uses a hybrid breeding cooperative particle swarm optimization algorithm to further refine the feature weight matrix and identify the optimal feature subset.The updated weight matrix is then fed back to the inner layer for further optimization.Comprehensive experiments on multiple real-world multi-label datasets demonstrate that Fed-MFSDHBCPSO consistently outperforms both centralized and federated baseline methods across several key evaluation metrics.
基金supported by the National Natural Science Foundation of China(62462040)the Yunnan Fundamental Research Projects(202501AT070345)the Major Science and Technology Projects in Yunnan Province(202202AD080013).
文摘Federated learning often experiences slow and unstable convergence due to edge-side data heterogeneity.This problem becomes more severe when edge participation rate is low,as the information collected from different edge devices varies significantly.As a result,communication overhead increases,which further slows down the convergence process.To address this challenge,we propose a simple yet effective federated learning framework that improves consistency among edge devices.The core idea is clusters the lookahead gradients collected from edge devices on the cloud server to obtain personalized momentum for steering local updates.In parallel,a global momentum is applied during model aggregation,enabling faster convergence while preserving personalization.This strategy enables efficient propagation of the estimated global update direction to all participating edge devices and maintains alignment in local training,without introducing extra memory or communication overhead.We conduct extensive experiments on benchmark datasets such as Cifar100 and Tiny-ImageNet.The results confirm the effectiveness of our framework.On CIFAR-100,our method reaches 55%accuracy with 37 fewer rounds and achieves a competitive final accuracy of 65.46%.Even under extreme non-IID scenarios,it delivers significant improvements in both accuracy and communication efficiency.The implementation is publicly available at https://github.com/sjmp525/CollaborativeComputing/tree/FedCCM(accessed on 20 October 2025).
基金supported by the National Natural Science Foundation of China(Grant No.62172123)the Key Research and Development Program of Heilongjiang Province,China(GrantNo.2022ZX01A36).
文摘Federated Learning(FL)protects data privacy through a distributed training mechanism,yet its decentralized nature also introduces new security vulnerabilities.Backdoor attacks inject malicious triggers into the global model through compromised updates,posing significant threats to model integrity and becoming a key focus in FL security.Existing backdoor attack methods typically embed triggers directly into original images and consider only data heterogeneity,resulting in limited stealth and adaptability.To address the heterogeneity of malicious client devices,this paper proposes a novel backdoor attack method named Capability-Adaptive Shadow Backdoor Attack(CASBA).By incorporating measurements of clients’computational and communication capabilities,CASBA employs a dynamic hierarchical attack strategy that adaptively aligns attack intensity with available resources.Furthermore,an improved deep convolutional generative adversarial network(DCGAN)is integrated into the attack pipeline to embed triggers without modifying original data,significantly enhancing stealthiness.Comparative experiments with Shadow Backdoor Attack(SBA)across multiple scenarios demonstrate that CASBA dynamically adjusts resource consumption based on device capabilities,reducing average memory usage per iteration by 5.8%.CASBA improves resource efficiency while keeping the drop in attack success rate within 3%.Additionally,the effectiveness of CASBA against three robust FL algorithms is also validated.
文摘ABSTRACT:Federated Learning(FL)enables collaborative medical model training without sharing sensitive patient data.However,existing FL systems face increasing security risks from post quantum adversaries and often incur nonnegligible computational and communication overhead when encryption is applied.At the same time,training high performance AI models requires large volumes of high quality data,while medical data such as patient information,clinical records,and diagnostic reports are highly sensitive and subject to strict privacy regulations,including HIPAA and GDPR.Traditional centralized machine learning approaches therefore pose significant challenges for cross institutional collaboration in healthcare.To address these limitations,Federated Learning was introduced to allow multiple institutions to jointly train a global model while keeping local data private.Nevertheless,conventional cryptographicmechanisms,such as RSA,are increasingly inadequate for privacy sensitive FL deployments,particularly in the presence of emerging quantum computing threats.Homomorphic encryption,which enables computations to be performed directly on encrypted data,provides an effective solution for preserving data privacy in federated learning systems.This capability allows healthcare institutions to securely perform collaborative model training while remaining compliant with regulatory requirements.Among homomorphic encryption techniques,NTRU,a lattice based cryptographic scheme defined over polynomial rings,offers strong resistance against quantum attacks by relying on the hardness of the Shortest Vector Problem(SVP).Moreover,NTRU supports limited homomorphic operations that are sufficient for secure aggregation in federated learning.In this work,we propose an NTRU enhanced federated learning framework specifically designed for medical and healthcare applications.Experimental results demonstrate that the proposed approach achieves classification performance comparable to standard federated learning,with final accuracy consistently exceeding 0.93.The framework introduces predictable encryption latency on the order of hundreds of milliseconds per training round and a fixed ciphertext communication overhead per client under practical deployment settings.In addition,the proposed systemeffectivelymitigatesmultiple security threats,including quantum computing attacks,by ensuring robust encryption throughout the training process.By integrating the security and homomorphic properties of NTRU,this study establishes a privacy preserving and quantumresistant federated learning framework that supports the secure,legal,and efficient deployment of AI technologies in healthcare,thereby laying a solid foundation for future intelligent healthcare systems.
文摘Nowadays,advances in communication technology and cloud computing have spawned a variety of smart mobile devices,which will generate a great amount of computing-intensive businesses,and require corresponding resources of computation and communication.Multiaccess edge computing(MEC)can offload computing-intensive tasks to the nearby edge servers,which alleviates the pressure of devices.Ultra-dense network(UDN)can provide effective spectrum resources by deploying a large number of micro base stations.Furthermore,network slicing can support various applications in different communication scenarios.Therefore,this paper integrates the ultra-dense network slicing and the MEC technology,and introduces a hybrid computing offloading strategy in order to satisfy various quality of service(QoS)of edge devices.In order to dynamically allocate limited resources,the above problem is formulated as multiagent distributed deep reinforcement learning(DRL),which will achieve low overhead computation offloading strategy and real-time resource allocation decisions.In this context,federated learning is added to train DRL agents in a distributed manner,where each agent is dedicated to exploring actions composed of offloading decisions and allocating resources,so as to jointly optimize system delay and energy consumption.Simulation results show that the proposed learning algorithm has better performance compared with other strategies in literature.
