Search Results for author: Shakila Tonni

Found 1 papers, 0 papers with code

Directional Privacy for Deep Learning

no code implementations9 Nov 2022 Pedro Faustini, Natasha Fernandes, Shakila Tonni, Annabelle McIver, Mark Dras

In this paper, we apply \textit{directional privacy}, via a mechanism based on the von Mises-Fisher (VMF) distribution, to perturb gradients in terms of \textit{angular distance} so that gradient direction is broadly preserved.

Cannot find the paper you are looking for? You can Submit a new open access paper.