Seminar, InfoSec Seminar: Towards Understanding Privacy Risks of Machine Learning Models

Speaker: Yang Zhang

Date/Time: 11-Mar-2020, 12:30 UTC

Venue: MPEB 6.12A.


Abstract: The past decade has witnessed the fast development of machine learning techniques, and the key factor that drives the current progress is the unprecedented large-scale data. On the one hand, machine learning and big data can help improve various domains of people's life quality. On the other hand, they can also cause severe risks to people's privacy. In this talk, I will present our research on assessing privacy risks caused by machine learning models. First, I will talk about our work on membership inference. Specifically, I will show how to relax the attacker’s assumptions to achieve a model and data independent membership inference attack against black-box machine learning models. Then, I will present our newest research on studying the privacy leakage of online learning. I will conclude the talk with a couple of directions I plan to pursue in the future.

Bio: Yang Zhang is a faculty member at CISPA Helmholtz Center for Information Security, Germany. His 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, USENIX Security, and IJCAI. His work has received NDSS 2019 distinguished paper award. Yang has served in the technical program committee of ACM CCS 2020 2019, WWW 2020, PETS 2021 2020, RAID 2020, and ISMB 2019.



Add to Calendar

This page was last modified on 27 Mar 2014.