Differential Privacy Has Disparate Impact on Model Accuracy
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 15453-15462, 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 in the neural networks trained using differentially private stochastic gradient ...More
PPT (Upload PPT)