Generating Differentially Private Datasets Using GANs

03/08/2018
by   Aleksei Triastcyn, et al.
0

In this paper, we present a technique for generating artificial datasets that retain statistical properties of the real data while providing differential privacy guarantees with respect to this data. We include a Gaussian noise layer in the discriminator of a generative adversarial network to make the output and the gradients differentially private with respect to the training data, and then use the generator component to synthesise privacy-preserving artificial dataset. Our experiments show that under a reasonably small privacy budget we are able to generate data of high quality and successfully train machine learning models on this artificial data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset