Four Facets of Differential Privacy

Differential privacy disentangles learning about a dataset as a whole from learning about an individual data contributor. Just now entering practice on a global scale, the demand for advanced differential privacy techniques and knowledge of basic skills is pressing. The Differential Privacy Symposium: Four Facets of Differential Privacy, held at the Institute for Advanced Study on November 12, 2016, provided an in-depth look at the current context for privacy-preserving statistical data analysis and an agenda for future research. This event was organized by Cynthia Dwork, of Microsoft Research, with support from the Alfred P. Sloan Foundation.


Institute Welcome by Robbert Dijkgraaf, Institute Director and Leon Levy Professor

Introduction: The Definition of Differential Privacy by Cynthia Dwork, Microsoft Research

Composition: The Key to Differential Privacy’s Success by Guy Rothblum, Weizmann Institute of Science and former Visitor in the School of Mathematics

Differentially Private Algorithms: Some Primitives and Paradigms by Kunal Talwar, Google Brain

Differential Privacy in Context: Conceptual and Ethical Considerations by Helen Nissenbaum, Cornell Tech and New York University

Rigorous Data Dredging: Theory and Tools for Adaptive Data Analysis by Aaron Roth, The University of Pennsylvania