Embedded Files
Title: Viewing Differential Privacy through the Lens of Information Theory
Time: 14:00-15:00 CEST, Tue Oct 24, 2023
Location: Systemet, B-huset 3rd floor, LiU Valla Campus, Linköping, Sweden
https://link.mazemap.com/bpxG7JDf
Local Host: Onur Günlü, LiU ISY Information Coding Division (ICG), onur.gunlu@liu.se
Abstract: Differential privacy (DP) has been one of the most widely studied and used frameworks for characterising privacy leakage from data sharing systems in both academia and industry. However, the leakage characteristics of differential privacy, especially in terms of Bayesian inference attacks, are not fully understood. In this talk, we utilise concepts from information theory to give an operational interpretation for the epsilon parameter in the local differential privacy (LDP) framework. Our characterisation establishes that epsilon in LDP is indeed an attainable upper bound on the worst-case Bayesian inference leakage from any data sharing system.
About the Speaker: Parastoo Sadeghi received the bachelor’s and master’s degrees in electrical engineering from Sharif University of Technology, Tehran, Iran, in 1995 and 1997, respectively, and the Ph.D. degree in electrical engineering from the University of New South Wales (UNSW), Sydney, in 2006. Parastoo is a Senior Member of IEEE and is currently a Professor with the School of Engineering and Information Technology, UNSW Canberra. She has co-authored over 200 refereed journal articles and conference papers. Her research interests include information theory, data privacy, index coding, and network coding. From 2016 to 2019, she served as an Associate Editor for the IEEE Transactions on Information Theory. In 2022, she was selected as a Distinguished Lecturer of the IEEE Information Theory Society. She is currently an ARC Future Fellow and is also serving as the Secretary of the IEEE Information Theory Society.
Summary of the IEEE ITSoc Distinguished Lecturer Talk
Parastoo Sadeghi of the University of New South Wales (UNSW), Canberra has visited the Information Theory and Security Laboratory (ITSL) within the Linköping University Information Coding Division (ICG) in Linköping, Sweden. This visit took place as a part of her travel as a Distinguished Lecturer of the IEEE Information Theory Society for 2022-2023. Parastoo talked about differential privacy and an operational interpretation of its epsilon parameter, which triggered extensive discussions with the audience who had a diverse background that included information theory, image coding, quantum information, quantum communications, and wireless communications. Parastoo's visit also included interesting discussions about Swedish history and academia, as well as lengthy discussions about index coding.
More about the ITSoc Distinguished Lecturer Program:
IEEE Information Theory Society established the Distinguished Lecturers Program to promote interest in information theory by supporting chapters that wish to invite prominent information theory researchers to give talks at their events. The selection criteria are (a) the quality of the candidates’ contributions to research in information theory and related areas, and (b) the ability of the candidates to deliver an excellent lecture to a broad audience.
Page updated
Google Sites
Report abuse