Revisiting the Provable-Auditable Privacy Gap of DP-SGD
A lightweight defense framework that generically augments optimization methods in the ML pipeline to have significantly-improved empirical privacy on standard benchmarks is given, and it is shown that the framework comes at no theoretical privacy cost when augmenting DP-SGD, unlike previously-proposed defenses against...
Saloni Modi, Srivi Balaji, Yu-Song Zhu et al.
· 0 citations