Differential Privacy Has Disparate Impact on Model Accuracy
arXiv: Learning, 2019.
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
PPT (Upload PPT)