Timezone: »

Renyi Differential Privacy Mechanisms for Posterior Sampling
Joseph Geumlek · Shuang Song · Kamalika Chaudhuri

Wed Dec 06:30 PM -- 10:30 PM PST @ Pacific Ballroom #68 #None

With the newly proposed privacy definition of Rényi Differential Privacy (RDP) in (Mironov, 2017), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating the influence of individual data points. In particular, we focus on sampling from an exponential family and specific generalized linear models, such as logistic regression. We propose novel RDP mechanisms as well as offering a new RDP analysis for an existing method in order to add value to the RDP framework. Each method is capable of achieving arbitrary RDP privacy guarantees, and we offer experimental results of their efficacy.

Author Information

Joseph Geumlek (UCSD)
Shuang Song (UC San Diego)

I am currently a 6th year PhD student in [UC San Diego](http://www.cs.ucsd.edu/). I am working with [Prof. Kamalika Chaudhuri](http://cseweb.ucsd.edu/~kamalika/) in Machine Learning and Differential Privacy. Before joining UCSD, I obtained my BSc degree in Mathematics and Computer Science from [The Hong Kong University of Science and Technology](http://www.ust.hk). I was an intern in the [Google Brain Team](https://research.google.com/teams/brain/) during Summer 2017.

Kamalika Chaudhuri (UCSD)

More from the Same Authors