Login / Signup
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks.
Lukas Struppek
Dominik Hintersdorf
Kristian Kersting
Published in:
ICLR (2024)
Keyphrases
</>
mathematical model
computational model
objective function
formal model
high level
prior knowledge
probabilistic model
privacy preserving
experimental data
neural network
multiscale