English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Decentralized Learning (DL) is a peer--to--peer learning approach that allowsa group of users to jointly train a machine learning model. To ensurecorrectness, DL should be robust, i.e., Byzantine users must not be able totamper with the result of the collaboration. In this paper, we introduce two\textit{new} attacks against DL where a Byzantine user can: make the networkconverge to an arbitrary model of their choice, and exclude an arbitrary userfrom the learning process. We demonstrate our attacks' efficiency againstSelf--Centered Clipping, the state--of--the--art robust DL protocol. Finally,we show that the capabilities decentralization grants to Byzantine users resultin decentralized learning \emph{always} providing less robustness thanfederated learning.

Can Decentralized Learning be more robust than Federated Learning?