Differentially Private Deep Learning with Smooth Sensitivity

Sun Lichao
Sun Lichao
Zhou Yingbo
Zhou Yingbo
Yu Philip S.
Yu Philip S.
Cited by: 0|Bibtex|Views6
Other Links: arxiv.org

Abstract:

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is through the lens of differential privacy. In this framework, privacy guarantees are generally obtained by perturbing models in such a way that specifics of data...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments