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 (FL) allows to train a massive amount of data privatelydue to its decentralized structure. Stochastic gradient descent (SGD) iscommonly used for FL due to its good empirical performance, but sensitive userinformation can still be inferred from weight updates shared during FLiterations. We consider Gaussian mechanisms to preserve local differentialprivacy (LDP) of user data in the FL model with SGD. The trade-offs betweenuser privacy, global utility, and transmission rate are proved by definingappropriate metrics for FL with LDP. Compared to existing results, the querysensitivity used in LDP is defined as a variable and a tighter privacyaccounting method is applied. The proposed utility bound allows heterogeneousparameters over all users. Our bounds characterize how much utility decreasesand transmission rate increases if a stronger privacy regime is targeted.Furthermore, given a target privacy level, our results guarantee asignificantly larger utility and a smaller transmission rate as compared toexisting privacy accounting methods.

Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communication