University of Cambridge > > Churchill CompSci Talks > Data anonymization and differential privacy

Data anonymization and differential privacy

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

If you have a question about this talk, please contact Matthew Ireland.

Data is money in computer science. It provides companies insights into user behaviour and is invaluable in medical research. But how is your privacy protected when your data is released into the public domain?

In this talk I will look at some basic ways to “anonymize” data and then show how we can attack these methods and give some examples of some high profile cases of these attacks. I will then introduce differential privacy, giving you an overview of the mathematical foundations that it stands on and some of its key properties that it guarantees when you use it to anonymise data.

This talk is part of the Churchill CompSci Talks 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