2 papers
cs.CR2023
A Cautionary Tale: On the Role of Reference Data in Empirical Privacy Defenses
Caelin G. Kaplan, Chuan Xu, Othmane Marfoq +2
Within the realm of privacy-preserving machine learning, empirical privacy defenses have been proposed as a solution to achieve satisfactory levels of training data privacy without…
cs.LG2023
Federated Learning under Heterogeneous and Correlated Client Availability
Angelo Rodio, Francescomaria Faticanti, Othmane Marfoq +2
The enormous amount of data produced by mobile and IoT devices has motivated the development of federated learning (FL), a framework allowing such devices (or clients) to collabora…