Privacy-Preserving Adversarial Networks

We address the problem of modifying a dataset so as to minimize mutual information about sensitive attributes in the released version, while maintaining a specified level of utility. This can be formulated as an optimization problem over distributions, and we attempt to solve it in a data-driven manner using adversarially trained neural networks. We will compare the performance of the data-driven approach to the theoretical optimum privacy-utility tradeoff for a simulated Gaussian dataset. Finally, we will see an application of this method on the MNIST digit dataset.
This is joint work with Ye Wang (MERL) and Prakash Ishwar (Boston University).
July 11 @ 16:00
4:00 pm (1h)

Memorial Union, State Room

Ardhendu Tripathy