Differential Privacy and the US Census - IPAM at UCLA
Institute for Pure & Applied Mathematics (IPAM) via YouTube
Overview
Explore the concept of differential privacy and its application to the 2020 US Census in this 58-minute lecture by Harvard University's Cynthia Dwork. Delve into the Fundamental Law of Information Reconstruction and understand why introducing noise is crucial for maintaining privacy in large datasets. Learn about the mathematically rigorous definition of differential privacy, its unique properties, and how it provides useful statistics while protecting against powerful adversaries. Discover the challenges faced by the US Census Bureau in implementing differential privacy for billions of statistics and the impact on traditional data consumption methods. Gain insights into the motivation behind differential privacy, its implementation, and its significance in balancing data utility and privacy protection in large-scale statistical analyses.
Syllabus
Cynthia Dwork - Differential Privacy and the US Census - IPAM at UCLA
Taught by
Institute for Pure & Applied Mathematics (IPAM)