Search Results for author: Timothée Ly

Found 1 papers, 0 papers with code

Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists

no code implementations18 Mar 2024 Timothée Ly, Julien Ferry, Marie-José Huguet, Sébastien Gambs, Ulrich Aivodji

Differentially-private (DP) mechanisms can be embedded into the design of a machine learningalgorithm to protect the resulting model against privacy leakage, although this often comes with asignificant loss of accuracy.

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