University of Cambridge > > Emmy Noether Society > Composition in Differential Privacy

Composition in Differential Privacy

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

If you have a question about this talk, please contact Kasia Warburton.

Last talk of term

A signal strength of Differential Privacy—a mathematically rigorous definition of privacy tailored to large datasets—is the ability not just to quantify privacy loss but also to analyze and control cumulative loss over multiple computations. In cryptographic terms, we understand how privacy loss “composes”. Not only is this crucial for the real-word use of data but it also gives rise to a rich algorithmic literature, as simple differentially private primitives can be combined in creative ways to construct complex differentially private analyses. This talk discusses recent analytical results in the composition of differentially private algorithms.

This talk is part of the Emmy Noether Society 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