Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models.

Florian A. Hölzl Daniel Rueckert Georgios Kaissis

Published in: AISec@CCS (2023)

Keyphrases

deep learning
differentially private
probabilistic model
data sets
machine learning
information retrieval
active learning
language model
privacy preserving
personal information
differential privacy