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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Federated Learning trains machine learning models on distributed devices byaggregating local model updates instead of local data. However, privacyconcerns arise as the aggregated local models on the server may revealsensitive personal information by inversion attacks. Privacy-preservingmethods, such as homomorphic encryption (HE), then become necessary for FLtraining. Despite HE's privacy advantages, its applications suffer fromimpractical overheads, especially for foundation models. In this paper, wepresent FedML-HE, the first practical federated learning system with efficientHE-based secure model aggregation. FedML-HE proposes to selectively encryptsensitive parameters, significantly reducing both computation and communicationoverheads during training while providing customizable privacy preservation.Our optimized system demonstrates considerable overhead reduction, particularlyfor large foundation models (e.g., ~10x reduction for ResNet-50, and up to ~40xreduction for BERT), demonstrating the potential for scalable HE-based FLdeployment.

FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System