Library for using the differential privacy for Gaussian processes framework
-
Updated
Nov 29, 2018 - Jupyter Notebook
Library for using the differential privacy for Gaussian processes framework
Adding Gaussian noise to gradient values of back propagation in order to make differntial privacy
An implementation of Priv'IT: Private and Sample Efficient Identity Testing
Simulate a federated setting and run differentially private federated learning.
Concentrated Differentially Private Gradient Descent with Adaptive per-iteration Privacy Budget
Add a description, image, and links to the dpgaussian topic page so that developers can more easily learn about it.
To associate your repository with the dpgaussian topic, visit your repo's landing page and select "manage topics."