Differential Privacy Has Disparate Impact on Model Accuracy

Eugene Bagdasaryan
Eugene Bagdasaryan

arXiv: Learning, 2019.

Cited by: 0|Bibtex|Views22
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Differential privacy (DP) is a popular mechanism for training machine learning models with bounded leakage about the presence of specific points in the training data. The cost of differential privacy is a reduction in the model's accuracy. We demonstrate that this cost is not borne equally: accuracy of DP models drops much more for the ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments