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

Distributed machine learning generally aims at training a global model basedon distributed data without collecting all the data to a centralized location,where two different approaches have been proposed: collecting and aggregatinglocal models (federated learning) and collecting and training overrepresentative data summaries (coreset). While each approach preserves dataprivacy to some extent thanks to not sharing the raw data, the exact extent ofprotection is unclear under sophisticated attacks that try to infer the rawdata from the shared information. We present the first comparison between thetwo approaches in terms of target model accuracy, communication cost, and dataprivacy, where the last is measured by the accuracy of a state-of-the-artattack strategy called the membership inference attack. Our experimentsquantify the accuracy-privacy-cost tradeoff of each approach, and reveal anontrivial comparison that can be used to guide the design of model trainingprocesses.

Sharing Models or Coresets: A Study based on Membership Inference Attack