University of Cambridge > > Machine Learning @ CUED > Differential Privacy Tutorial

Differential Privacy Tutorial

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Alexander Matthews.


Differential privacy is the dominant theory of statistical analysis under constraints of individual privacy preservation. In the first section, which will constitute the majority of the talk, we will introduce the basic concepts of Differential Privacy and its motivation. It will be similar to the first chapters of

1) The Algorithmic Foundations of Differential Privacy. Dwork and Roth. 2014

However, since our talk is introductory in nature no prior reading will be necessary.

To give a flavour of recent research, we will then give a brief overview of two recent papers on the topic specifically:

2) Deep Learning with Differential Privacy. Abadi et al. 2016

3) Differential Privacy For Functions and Functional Data. Hall et al. 2013

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity