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

The idea of federated learning is to train deep neural network modelscollaboratively and share them with multiple participants without exposingtheir private training data to each other. This is highly attractive in themedical domain due to patients' privacy records. However, a recently proposedmethod called Deep Leakage from Gradients enables attackers to reconstruct datafrom shared gradients. This study shows how easy it is to reconstruct imagesfor different data initialization schemes and distance measures. We show howdata and model architecture influence the optimal choice of initializationscheme and distance measure configurations when working with single images. Wedemonstrate that the choice of initialization scheme and distance measure cansignificantly increase convergence speed and quality. Furthermore, we find thatthe optimal attack configuration depends largely on the nature of the targetimage distribution and the complexity of the model architecture.

Analysing the Influence of Attack Configurations on the Reconstruction of Medical Images in Federated Learning