MPI-INF Logo
Campus Event Calendar

Event Entry

What and Who

Security and Privacy Guarantees in Machine Learning with Differential Privacy

Roxana Geambasu
Columbia University
SWS Distinguished Lecture Series

Roxana Geambasu is an Associate Professor of Computer Science at Columbia University and a member of Columbia's Data Sciences Institute. She joined Columbia in Fall 2011 after finishing her Ph.D. at the University of Washington. For her work in cloud and mobile data privacy, she received: an Alfred P. Sloan Faculty Fellowship, an NSF CAREER award, a Microsoft Research Faculty Fellowship, several Google Faculty awards, a "Brilliant 10" Popular Science nomination, the Honorable Mention for the 2013 inaugural Dennis M. Ritchie Doctoral Dissertation Award, a William Chan Dissertation Award, two best paper awards at top systems conferences, and the first Google Ph.D. Fellowship in Cloud Computing
AG 3, SWS, RG1, MMCI  
AG Audience
English

Date, Time and Location

Monday, 15 June 2020
16:00
60 Minutes
E1 4
Zoom
Saarbrücken

Abstract

Abstract:
Machine learning (ML) is driving many of our applications and life-changing decisions. Yet, it is often brittle and unstable, making decisions that are hard to understand or can be exploited. Tiny changes to an input can cause dramatic changes in predictions; this results in decisions that surprise, appear unfair, or enable attack vectors such as adversarial examples. Moreover, models trained on users' data can encode not only general trends from large datasets but also very specific, personal information from these datasets; this threatens to expose users' secrets through ML models or predictions. This talk positions differential privacy (DP) -- a rigorous privacy theory -- as a versatile foundation for building into ML much-needed guarantees of security, stability, and privacy. I first present PixelDP (S&P'19), a scalable certified defense against adversarial example attacks that leverages DP theory to guarantee a level of robustness against these attacks. I then present Sage (SOSP'19), a DP ML platform that bounds the cumulative leakage of secrets through models while addressing some of the most pressing challenges of DP, such as running out of privacy budget and the privacy-accuracy tradeoff. PixelDP and Sage are designed from a pragmatic, systems perspective and illustrate that DP theory is powerful but requires adaptation to achieve practical guarantees for ML workloads.

Contact

Danielle Dalton
+49 681 9303 9106
--email hidden
passcode not visible
logged in users only

Danielle Dalton, 06/09/2020 12:00 -- Created document.