pith. sign in

arxiv: 2005.13099 · v5 · pith:2WI4T6XQnew · submitted 2020-05-27 · 💻 cs.LG · cs.CR· cs.CV· eess.IV· stat.ML

Benchmarking Differentially Private Residual Networks for Medical Imagery

classification 💻 cs.LG cs.CRcs.CVeess.IVstat.ML
keywords medicalprivacydifferentialguaranteesimagerywhenaccuracyactually
0
0 comments X
read the original abstract

In this paper we measure the effectiveness of $\epsilon$-Differential Privacy (DP) when applied to medical imaging. We compare two robust differential privacy mechanisms: Local-DP and DP-SGD and benchmark their performance when analyzing medical imagery records. We analyze the trade-off between the model's accuracy and the level of privacy it guarantees, and also take a closer look to evaluate how useful these theoretical privacy guarantees actually prove to be in the real world medical setting.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.