Show simple item record

AuthorGouissem, A.
AuthorAbualsaud, K.
AuthorYaacoub, E.
AuthorKhattab, T.
AuthorGuizani, M.
Available date2022-10-19T07:27:04Z
Publication Date2022-01-01
Publication NameIEEE Wireless Communications and Networking Conference, WCNC
Identifierhttp://dx.doi.org/10.1109/WCNC51071.2022.9771594
CitationGouissem, A., Abualsaud, K., Yaacoub, E., Khattab, T., & Guizani, M. (2022, April). Federated Learning Stability Under Byzantine Attacks. In 2022 IEEE Wireless Communications and Networking Conference (WCNC) (pp. 572-577). IEEE.‏
ISBN9781665442664
ISSN15253511
URIhttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85130750457&origin=inward
URIhttp://hdl.handle.net/10576/35197
AbstractFederated Learning (FL) is a machine learning approach that enables private and decentralized model training. Although FL has been shown to be very useful in several applications, its privacy constraints cause a lack of model update transparency which makes it vulnerable to several types of attacks. In particular, based on detailed convergence analyses, we show in this paper that when the traditional model-combining scheme is used, even a single Byzantine node that keeps sending random reports will cause the whole FL model to diverge to non-useful solutions. A low complexity model combining approach is also proposed to stabilize the FL system and make it converge to a suboptimal solution just by controlling the model norm. The Physikalisch-Technische Bundesanstalt extra-large electrocardiogram (PTB-XL ECG) dataset is used to validate the findings of this paper and show the efficiency of the proposed approach in identifying heart anomalies.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectByzantine attacks
Convergence analysis
Distributed Learning
E-health
Federated Learning
TitleFederated Learning Stability Under Byzantine Attacks
TypeConference Paper
Pagination572-577
Volume Number2022-April


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record