Achieving security and privacy in federated learning systems: Survey, research challenges and future directions

Federated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their privat...

Descripción completa

Detalles Bibliográficos
Autores: Blanco-Justicia, Alberto, Domingo-Ferrer, Josep, Martínez Lluís, Sergio, Sánchez Ruenes, David, Flanagan, Adrian, Tan, Kuan Eik
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2021
País:España
Institución:Universitat Oberta de Catalunya (UOC)
Repositorio:O2, repositorio institucional de la UOC
OAI Identifier:oai:openaccess.uoc.edu:10609/136566
Acceso en línea:https://hdl.handle.net/10609/136566
Access Level:acceso abierto
Palabra clave:federated learning
machine learning
privacy
security
aprendizaje automático
privacidad
seguridad
aprendizaje federado
aprenentatge automàtic
privacitat
seguretat
aprenentatge federat
Machine learning
Aprenentatge automàtic
Aprendizaje automático
id ES_ee83bffaffdcfade2cadb2d8c2d112fb
oai_identifier_str oai:openaccess.uoc.edu:10609/136566
network_acronym_str ES
network_name_str España
repository_id_str
spelling Achieving security and privacy in federated learning systems: Survey, research challenges and future directionsBlanco-Justicia, AlbertoDomingo-Ferrer, JosepMartínez Lluís, SergioSánchez Ruenes, DavidFlanagan, AdrianTan, Kuan Eikfederated learningmachine learningprivacysecurityaprendizaje automáticoprivacidadseguridadaprendizaje federadoaprenentatge automàticprivacitatseguretataprenentatge federatMachine learningAprenentatge automàticAprendizaje automáticoFederated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their private data to the server. However, FL is not free of issues. On the one hand, the model updates sent by the clients at each training epoch might leak information on the clients' private data. On the other hand, the model learnt by the server may be subjected to attacks by malicious clients; these security attacks might poison the model or prevent it from converging. In this paper, we first examine security and privacy attacks to FL and critically survey solutions proposed in the literature to mitigate each attack. Afterwards, we discuss the difficulty of simultaneously achieving security and privacy protection. Finally, we sketch ways to tackle this open problem and attain both security and privacy.Engineering Applications of Artificial IntelligenceUniversitat Oberta de Catalunya (UOC)Universitat Rovira i Virgili (URV)Huawei Technologies202120212021info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://hdl.handle.net/10609/136566reponame:O2, repositorio institucional de la UOCinstname:Universitat Oberta de Catalunya (UOC)InglésEngineering Applications of Artificial Intelligence, 2021, 106https://doi.org/10.1016/j.engappai.2021.104468info:eu-repo/grantAgreement/YBN2019035188//info:eu-repo/grantAgreement/H2020-871042//info:eu-repo/grantAgreement/H2020-101006879//info:eu-repo/grantAgreement/2017 SGR 705//info:eu-repo/grantAgreement/RTI2018-095094-B-C21//info:eu-repo/grantAgreement/TIN2016-80250-R//CC BY-NC-NDhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:openaccess.uoc.edu:10609/1365662026-05-28T12:42:01Z
dc.title.none.fl_str_mv Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
title Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
spellingShingle Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
Blanco-Justicia, Alberto
federated learning
machine learning
privacy
security
aprendizaje automático
privacidad
seguridad
aprendizaje federado
aprenentatge automàtic
privacitat
seguretat
aprenentatge federat
Machine learning
Aprenentatge automàtic
Aprendizaje automático
title_short Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
title_full Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
title_fullStr Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
title_full_unstemmed Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
title_sort Achieving security and privacy in federated learning systems: Survey, research challenges and future directions
dc.creator.none.fl_str_mv Blanco-Justicia, Alberto
Domingo-Ferrer, Josep
Martínez Lluís, Sergio
Sánchez Ruenes, David
Flanagan, Adrian
Tan, Kuan Eik
author Blanco-Justicia, Alberto
author_facet Blanco-Justicia, Alberto
Domingo-Ferrer, Josep
Martínez Lluís, Sergio
Sánchez Ruenes, David
Flanagan, Adrian
Tan, Kuan Eik
author_role author
author2 Domingo-Ferrer, Josep
Martínez Lluís, Sergio
Sánchez Ruenes, David
Flanagan, Adrian
Tan, Kuan Eik
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universitat Oberta de Catalunya (UOC)
Universitat Rovira i Virgili (URV)
Huawei Technologies
dc.subject.none.fl_str_mv federated learning
machine learning
privacy
security
aprendizaje automático
privacidad
seguridad
aprendizaje federado
aprenentatge automàtic
privacitat
seguretat
aprenentatge federat
Machine learning
Aprenentatge automàtic
Aprendizaje automático
topic federated learning
machine learning
privacy
security
aprendizaje automático
privacidad
seguridad
aprendizaje federado
aprenentatge automàtic
privacitat
seguretat
aprenentatge federat
Machine learning
Aprenentatge automàtic
Aprendizaje automático
description Federated learning (FL) allows a server to learn a machine learning (ML) model across multiple decentralized clients that privately store their own training data. In contrast with centralized ML approaches, FL saves computation to the server and does not require the clients to outsource their private data to the server. However, FL is not free of issues. On the one hand, the model updates sent by the clients at each training epoch might leak information on the clients' private data. On the other hand, the model learnt by the server may be subjected to attacks by malicious clients; these security attacks might poison the model or prevent it from converging. In this paper, we first examine security and privacy attacks to FL and critically survey solutions proposed in the literature to mitigate each attack. Afterwards, we discuss the difficulty of simultaneously achieving security and privacy protection. Finally, we sketch ways to tackle this open problem and attain both security and privacy.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://hdl.handle.net/10609/136566
url https://hdl.handle.net/10609/136566
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Engineering Applications of Artificial Intelligence, 2021, 106
https://doi.org/10.1016/j.engappai.2021.104468
info:eu-repo/grantAgreement/YBN2019035188//
info:eu-repo/grantAgreement/H2020-871042//
info:eu-repo/grantAgreement/H2020-101006879//
info:eu-repo/grantAgreement/2017 SGR 705//
info:eu-repo/grantAgreement/RTI2018-095094-B-C21//
info:eu-repo/grantAgreement/TIN2016-80250-R//
dc.rights.none.fl_str_mv CC BY-NC-ND
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv CC BY-NC-ND
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Engineering Applications of Artificial Intelligence
publisher.none.fl_str_mv Engineering Applications of Artificial Intelligence
dc.source.none.fl_str_mv reponame:O2, repositorio institucional de la UOC
instname:Universitat Oberta de Catalunya (UOC)
instname_str Universitat Oberta de Catalunya (UOC)
reponame_str O2, repositorio institucional de la UOC
collection O2, repositorio institucional de la UOC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423702855122944
score 15.300724

Similares en LA Referencia