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
Face authentication is an important biometric authentication method commonly used in security applications.It is vulnerable to different types of attacks that use authorized users’facial images and videos captured fr...Face authentication is an important biometric authentication method commonly used in security applications.It is vulnerable to different types of attacks that use authorized users’facial images and videos captured from social media to perform spoofing attacks and dynamic movements for penetrating secur-ity applications.This paper presents an innovative challenge-response emotions authentication model based on the horizontal ensemble technique.The proposed model provides high accurate face authentication process by challenging the authorized user using a random sequence of emotions to provide a specific response for every authentication trial with a different sequence of emotions.The proposed model is applied to the KDEF dataset using 10-fold cross-valida-tions.Several improvements are made to the proposed model.First,the VGG16 model is applied to the seven common emotions.Second,the system usability is enhanced by analyzing and selecting only the four common and easy-to-use emotions.Third,the horizontal ensemble technique is applied to enhance the emotion recognition accuracy and minimize the error during authen-tication processes.Finally,the Horizontal Ensemble Best N-Losses(HEBNL)is applied using challenge-response emotion to improve the authentication effi-ciency and minimize the computational power.The successive improvements implemented on the proposed model led to an improvement in the accuracy from 92.1%to 99.27%.展开更多
The medical industry generates vast amounts of data suitable for machine learning during patient-clinician interaction in hospitals.However,as a result of data protection regulations like the general data protection r...The medical industry generates vast amounts of data suitable for machine learning during patient-clinician interaction in hospitals.However,as a result of data protection regulations like the general data protection regulation(GDPR),patient data cannot be shared freely across institutions.In these cases,federated learning(FL)is a viable option where a global model learns from multiple data sites without moving the data.In this paper,we focused on random forests(RFs)for its effectiveness in classification tasks and widespread use throughout the medical industry and compared two popular federated random forest aggregation algorithms on horizontally partitioned data.We first provided necessary background information on federated learning,the advantages of random forests in a medical context,and the two aggregation algorithms.A series of extensive experiments using four public binary medical datasets(an excerpt of MIMIC III,Pima Indian diabetes dataset from Kaggle,and diabetic retinopathy and heart failure dataset from UCI machine learning repository)were then performed to systematically compare the two on equal-sized,unequal-sized,and class-imbalanced clients.A follow-up investigation on the effects of more clients was also conducted.We finally empirically analyzed the advantages of federated learning and concluded that the weighted merge algorithm produces models with,on average,1.903%higher F1 score and 1.406%higher AUCROC value.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.
基金This work is partially supported by the Deanship of Scientific Research at Jouf University under Grant No(DSR-2021–02–0369).
文摘Face authentication is an important biometric authentication method commonly used in security applications.It is vulnerable to different types of attacks that use authorized users’facial images and videos captured from social media to perform spoofing attacks and dynamic movements for penetrating secur-ity applications.This paper presents an innovative challenge-response emotions authentication model based on the horizontal ensemble technique.The proposed model provides high accurate face authentication process by challenging the authorized user using a random sequence of emotions to provide a specific response for every authentication trial with a different sequence of emotions.The proposed model is applied to the KDEF dataset using 10-fold cross-valida-tions.Several improvements are made to the proposed model.First,the VGG16 model is applied to the seven common emotions.Second,the system usability is enhanced by analyzing and selecting only the four common and easy-to-use emotions.Third,the horizontal ensemble technique is applied to enhance the emotion recognition accuracy and minimize the error during authen-tication processes.Finally,the Horizontal Ensemble Best N-Losses(HEBNL)is applied using challenge-response emotion to improve the authentication effi-ciency and minimize the computational power.The successive improvements implemented on the proposed model led to an improvement in the accuracy from 92.1%to 99.27%.
文摘The medical industry generates vast amounts of data suitable for machine learning during patient-clinician interaction in hospitals.However,as a result of data protection regulations like the general data protection regulation(GDPR),patient data cannot be shared freely across institutions.In these cases,federated learning(FL)is a viable option where a global model learns from multiple data sites without moving the data.In this paper,we focused on random forests(RFs)for its effectiveness in classification tasks and widespread use throughout the medical industry and compared two popular federated random forest aggregation algorithms on horizontally partitioned data.We first provided necessary background information on federated learning,the advantages of random forests in a medical context,and the two aggregation algorithms.A series of extensive experiments using four public binary medical datasets(an excerpt of MIMIC III,Pima Indian diabetes dataset from Kaggle,and diabetic retinopathy and heart failure dataset from UCI machine learning repository)were then performed to systematically compare the two on equal-sized,unequal-sized,and class-imbalanced clients.A follow-up investigation on the effects of more clients was also conducted.We finally empirically analyzed the advantages of federated learning and concluded that the weighted merge algorithm produces models with,on average,1.903%higher F1 score and 1.406%higher AUCROC value.
