Quantifying Privacy Risks of Machine Learning Models
The ViSP Distinguished Lecture Series continues with a talk by Yang Zhang of CISPA Helmholtz Center for Information Security, Germany.
This is an online-only event.
See description for details.
Yang Zhang is a faculty member at CISPA Helmholtz Center for Information Security, Germany. Previously, he was a group leader at CISPA. He obtained his Ph.D. degree from University of Luxembourg in November 2016. Yang’s research interests lie at the intersection of privacy and machine learning. Over the years, he has published multiple papers at top venues in computer science, including WWW, CCS, NDSS, and USENIX Security. His work has received the NDSS 2019 distinguished paper award.
Machine learning has made tremendous progress during the past decade. While continuing to improve our daily lives, recent research shows that machine learning models are vulnerable to various privacy attacks. In this talk, I will cover our three recent works on quantifying the privacy risks of machine learning models. First, I will talk about some recent development of membership inference. Second, I will discuss the data reconstruction attacks against online learning. In the end, I will present link stealing attacks against graph neural networks.
Join us via Zoom: tuwien.zoom.us/j/91926100499
About The Lecture Series
ViSP is organizing a Distinguished Lecture Series with internationally renowned researchers from the field of Security & Privacy. Every month there will be a talk on a current research topic, followed by an open discussion.
ViSP, the Vienna Cybersecurity and Privacy Research Center, consists of researchers from IST Austria, TU Wien and Uni Wien. With these three institutes, Vienna offers an exceptional degree of excellence for research in the area of Security and Privacy. The mission of ViSP is to unlock the true potential of the location by fostering collaborations between different institutes in Vienna. This collaboration strives to do impactful research and advance state of the art, securing Vienna’s pioneer role in the research in Security and Privacy.