[ML Seminars] Learning and privacy

Christos Dimitrakakis talks about the challenge of identity protection.

If we wish to publish a database, or an analysis based on it, we must protect identities of people involved. Erasing directly identifying informationdoes not really work most of the time, especially since attackers can have side-information that can reveal the identities of individuals in the original data. While k-anonymity can protect against specific re-identification attacks when used with care, it says little about what to do when the adversary has a lot of power. In this talk, we introduce the concept of differential privacy, which offers protection against adversaries with unlimited side-information or computational power. Informally, an algorithmic computation is differentially-private if an adversary cannot distinguish two similar database based on the result of the computation. We then discuss its application to both theoretical and practical problems in machine learning.

Tags: Machine Learning, privacy, Maskinlæring, personvern
Published Jan. 31, 2019 9:54 AM - Last modified Jan. 31, 2019 10:28 AM