![](/sites/default/files/styles/workshop_banner_sm_1x/public/privacy_logo_padded_0.png.jpg?itok=K6Hm3Buh)
Abstract
A brief tutorial and demo on using TF Privacy, Tensorflow's open-source library for differentially private stochastic gradient descent (DP-SGD). We will show how to easily write code that implements DP-SGD, talk about practical considerations in training, and show how to analyze the privacy parameters of the resulting model.