Recent works have shown that selecting an optimal model architecture suited to the differential privacy setting is necessary to achieve the best possible utility for a given privacy budget using differentially private stochastic gradient descent (DP-SGD)(Tramèr and Boneh 2020; Cheng et al. 2022). In light of these findings, we empirically...
-
February 13, 2023 (v1)Conference paperUploaded on: January 17, 2024
-
July 15, 2024 (v1)Conference paper
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 a significant drop in model utility. Most existing defenses against membership inference attacks assume access to reference data, defined as an additional dataset...
Uploaded on: November 5, 2024