Abstract 

I will introduce privacy work of FCAI research programme in Privacy-preserving and secure AI. Our goal is to develop methods that allow learning from data under strong differential privacy guarantees. These enable setting strict limits on how much an adversary can learn about an individual contributing to a data set from the outcome of a computation using that data set. After a general overview, I will discuss differentially private data anonymisation.

Speaker: Antti Honkela
Affiliation: Associate Professor, Department of Computer Science, University of Helsinki

Machine Learning Coffee seminars are weekly seminars organized by Finnish Center for Artificial Intelligence (FCAI) and are held jointly by the Aalto University and the University of Helsinki. The seminars aim to gather people from different fields of science with interest in machine learning. Seminars will be held weekly on Mondays at 9:00-10:00. The location alternates between Aalto University and the University of Helsinki. At Aalto University, talks will be held in Konemiehentie 2, seminar room T6 and at the University of Helsinki in Kumpula, seminar room Exactum D122 (Gustaf Hällströmin katu 2b), unless otherwise noted. Talks will begin at 9:15 and coffee will be served from 9:00.