Collaborative Byzantine Resilient Federated Learning

<p dir="ltr">Federated learning (FL) enables an effective and private distributed learning process. However, it is vulnerable against several types of attacks, such as Byzantine behaviors. The first purpose of this work is to demonstrate mathematically that the traditional arithmetic...

Full description

Saved in:
Bibliographic Details
Main Author: A. Gouissem (17541396) (author)
Other Authors: K. Abualsaud (17541399) (author), E. Yaacoub (17541402) (author), T. Khattab (17541405) (author), M. Guizani (17541408) (author)
Published: 2023
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513535663407104
author A. Gouissem (17541396)
author2 K. Abualsaud (17541399)
E. Yaacoub (17541402)
T. Khattab (17541405)
M. Guizani (17541408)
author2_role author
author
author
author
author_facet A. Gouissem (17541396)
K. Abualsaud (17541399)
E. Yaacoub (17541402)
T. Khattab (17541405)
M. Guizani (17541408)
author_role author
dc.creator.none.fl_str_mv A. Gouissem (17541396)
K. Abualsaud (17541399)
E. Yaacoub (17541402)
T. Khattab (17541405)
M. Guizani (17541408)
dc.date.none.fl_str_mv 2023-04-11T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/jiot.2023.3266347
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Collaborative_Byzantine_Resilient_Federated_Learning/24717186
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Data management and data science
Distributed computing and systems software
Machine learning
Training
Data models
Convergence
Computational modeling
Internet of Things
Servers
Predictive models
dc.title.none.fl_str_mv Collaborative Byzantine Resilient Federated Learning
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Federated learning (FL) enables an effective and private distributed learning process. However, it is vulnerable against several types of attacks, such as Byzantine behaviors. The first purpose of this work is to demonstrate mathematically that the traditional arithmetic-averaging model-combining approach will ultimately diverge to an unstable solution in the presence of Byzantine agents. This article also proposes a low-complexity, decentralized Byzantine resilient training mechanism. The proposed technique identifies and isolates hostile nodes rather than just mitigating their impact on the global model. In addition, the suggested approach may be used alone or in conjunction with other protection techniques to provide an additional layer of security in the event of misdetection. The suggested solution is decentralized, allowing all participating nodes to jointly identify harmful individuals using a novel cross check mechanism. To prevent biased assessments, the identification procedure is done blindly and is incorporated into the regular training process. A smart activation mechanism based on flag activation is also proposed to reduce the network overhead. Finally, general mathematical proofs combined with extensive experimental results applied in a healthcare electrocardiogram (ECG) monitoring scenario show that the proposed techniques are very efficient at accurately predicting heart problems.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Internet of Things Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jiot.2023.3266347" target="_blank">https://dx.doi.org/10.1109/jiot.2023.3266347</a></p>
eu_rights_str_mv openAccess
id Manara2_a8b82cb60e405a7ba54e2c46f55b5dbe
identifier_str_mv 10.1109/jiot.2023.3266347
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24717186
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Collaborative Byzantine Resilient Federated LearningA. Gouissem (17541396)K. Abualsaud (17541399)E. Yaacoub (17541402)T. Khattab (17541405)M. Guizani (17541408)Information and computing sciencesData management and data scienceDistributed computing and systems softwareMachine learningTrainingData modelsConvergenceComputational modelingInternet of ThingsServersPredictive models<p dir="ltr">Federated learning (FL) enables an effective and private distributed learning process. However, it is vulnerable against several types of attacks, such as Byzantine behaviors. The first purpose of this work is to demonstrate mathematically that the traditional arithmetic-averaging model-combining approach will ultimately diverge to an unstable solution in the presence of Byzantine agents. This article also proposes a low-complexity, decentralized Byzantine resilient training mechanism. The proposed technique identifies and isolates hostile nodes rather than just mitigating their impact on the global model. In addition, the suggested approach may be used alone or in conjunction with other protection techniques to provide an additional layer of security in the event of misdetection. The suggested solution is decentralized, allowing all participating nodes to jointly identify harmful individuals using a novel cross check mechanism. To prevent biased assessments, the identification procedure is done blindly and is incorporated into the regular training process. A smart activation mechanism based on flag activation is also proposed to reduce the network overhead. Finally, general mathematical proofs combined with extensive experimental results applied in a healthcare electrocardiogram (ECG) monitoring scenario show that the proposed techniques are very efficient at accurately predicting heart problems.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Internet of Things Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jiot.2023.3266347" target="_blank">https://dx.doi.org/10.1109/jiot.2023.3266347</a></p>2023-04-11T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/jiot.2023.3266347https://figshare.com/articles/journal_contribution/Collaborative_Byzantine_Resilient_Federated_Learning/24717186CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/247171862023-04-11T06:00:00Z
spellingShingle Collaborative Byzantine Resilient Federated Learning
A. Gouissem (17541396)
Information and computing sciences
Data management and data science
Distributed computing and systems software
Machine learning
Training
Data models
Convergence
Computational modeling
Internet of Things
Servers
Predictive models
status_str publishedVersion
title Collaborative Byzantine Resilient Federated Learning
title_full Collaborative Byzantine Resilient Federated Learning
title_fullStr Collaborative Byzantine Resilient Federated Learning
title_full_unstemmed Collaborative Byzantine Resilient Federated Learning
title_short Collaborative Byzantine Resilient Federated Learning
title_sort Collaborative Byzantine Resilient Federated Learning
topic Information and computing sciences
Data management and data science
Distributed computing and systems software
Machine learning
Training
Data models
Convergence
Computational modeling
Internet of Things
Servers
Predictive models