Improved Accounting for Differentially Private Learning

01/28/2019
by   Aleksei Triastcyn, et al.
0

We consider the problem of differential privacy accounting, i.e. estimation of privacy loss bounds, in machine learning in a broad sense. We propose two versions of a generic privacy accountant suitable for a wide range of learning algorithms. Both versions are derived in a simple and principled way using well-known tools from probability theory, such as concentration inequalities. We demonstrate that our privacy accountant is able to achieve state-of-the-art estimates of DP guarantees and can be applied to new areas like variational inference. Moreover, we show that the latter enjoys differential privacy at minor cost.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset