Privacy Risks of Releasing High Dimensional Models

This post addresses the “so what?” question of our work on privacy in probabilistic graphical models. This is not a detailed explanation of the paper. If you are interested in the technical details of the paper, please read our full work here. In this post, I focus on two very important questions of any research problem:

1) Why this problem? (What are we expecting to discover/learn by solving this problem?)
2) So what? (What is the meaning of this solution? What is it saying?)

We study extreme cases so that we can understand what is normal better.

Work under progress ….