Talk: Alexandre Graell i Amat (July 08, 2025 at 10:00 AM, Seminar room N2407, Zoom)
Talks |
Are You in the Training Set? Membership Inference and the Art of Attacking Machine Learning Models
Prof. Alexandre Graell i Amat
Chalmers University of Technology
Abstract:
This talk is the second part of a two-hour seminar on membership inference attacks (MIAs). If you missed the first part but would like to join this one, don't worry, I will provide a brief 10-minute recap at the beginning. This introduction will cover the motivation behind MIAs and their core definition, giving you the necessary context to follow the rest of the session.
While the recap won’t cover all details from the first part, it will provide enough foundation to engage with the material in the second part. Also, no background in machine learning is assumed.
In this session, we will explore two additional influential papers on MIAs, present some of our own contributions to the field, and highlight open problems that remain unsolved. I will also comment on a point made by Emma: how membership inference attacks can remain effective even when the adversary has access only to the predicted class labels, rather than the full confidence scores or logits.
Biography:
Alexandre Graell i Amat is Professor with the Communication Systems group. His research interests are in the area of (modern) coding theory and cover a broad range of topics, including distributed storage, caching, and distributed computing, and optical communications.
Prof. Graell i Amat received the MSc degree in Telecommunications Engineering from the Universitat Politècnica de Catalunya, Barcelona, Catalonia, Spain, in 2001, and the MSc and the PhD degrees in Electrical Engineering from the Politecnico di Torino, Turin, Italy, in 2000 and 2004, respectively. Previously to joining Chalmers in 2011, he was with ENST Bretagne, Brest, France, from 2006 to 2010, first as a Marie Curie Fellow and then as an Associate Professor.
Prof. Graell i Amat is Editor at Large for the IEEE Transactions on Communications. Previously, he served as Associate Editor for the IEEE Transactions on Communications (2011-2016) and for the IEEE Communications Letters (2011-2013). He was the General Co-Chair of the 7th International Symposium on Turbo Codes & Iterative Information Processing, 2012, the Swedish Communication Technologies Workshop 2013, and the IEEE European School of Information Theory, 2016.
Prof. Graell i Amat is the recipient of the 2010 IEEE ComSoc Best Young Researcher Award for the Europe, Middle East, and Africa Region, and of a Marie Curie Intra-European Fellowship (2006-2008) by the European Commission. He is co-author of a paper that won the 2016 IEEE Sweden VT-COM-IT joint chapter best student conference paper award.
Zoom: https://tum-conf.zoom-x.de/j/68460493253?pwd=nFaxyZdWGLaatWbhDDr0N21xNJ79f1.1 (Meeting ID: 684 6049 3253, Passcode: 152491)