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

Deep learning techniques have achieved remarkable performance in wide-rangingtasks. However, when trained on privacy-sensitive datasets, the modelparameters may expose private information in training data. Prior attempts fordifferentially private training, although offering rigorous privacy guarantees,lead to much lower model performance than the non-private ones. Besides,different runs of the same training algorithm produce models with largeperformance variance. To address these issues, we propose DPlis--DifferentiallyPrivate Learning wIth Smoothing. The core idea of DPlis is to construct asmooth loss function that favors noise-resilient models lying in large flatregions of the loss landscape. We provide theoretical justification for theutility improvements of DPlis. Extensive experiments also demonstrate thatDPlis can effectively boost model quality and training stability under a givenprivacy budget.

DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing