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

Federated learning is considered as an effective privacy-preserving learningmechanism that separates the client's data and model training process. However,federated learning is still under the risk of privacy leakage because of theexistence of attackers who deliberately conduct gradient leakage attacks toreconstruct the client data. Recently, popular strategies such as gradientperturbation methods and input encryption methods have been proposed to defendagainst gradient leakage attacks. Nevertheless, these defenses can eithergreatly sacrifice the model performance, or be evaded by more advanced attacks.In this paper, we propose a new defense method to protect the privacy ofclients' data by learning to obscure data. Our defense method can generatesynthetic samples that are totally distinct from the original samples, but theycan also maximally preserve their predictive features and guarantee the modelperformance. Furthermore, our defense strategy makes the gradient leakageattack and its variants extremely difficult to reconstruct the client data.Through extensive experiments, we show that our proposed defense method obtainsbetter privacy protection while preserving high accuracy compared withstate-of-the-art methods.

Defense Against Gradient Leakage Attacks via Learning to Obscure Data