I'm In the Database (But Nobody Knows) (Cynthia Dwork)

UC Berkeley School of Information

“Your data will only be used in aggregated form.” What does this statement mean, and why is it so often included in privacy policies? Drawing from examples in the popular press and the technical literature, the talk will scrutinize the common intuition that privacy is ensured by aggregation and show that information — and hence privacy loss — flows in mysterious ways. Arguing that the situation demands a mathematically rigorous treatment of privacy, the talk will introduce “differential privacy,” a field of research supporting a strong definition of privacy tailored to analysis of large data sets. This still-growing approach is thriving and is beginning to enter practice. Bio: Cynthia Dwork, a distinguished scientist at Microsoft Research, is renowned for placing privacy-preserving data analysis on a mathematically rigorous foundation. A cornerstone of this work is differential privacy, a strong privacy guarantee frequently permitting highly accurate data analysis. Dr. Dwork has also made seminal contributions in cryptography and distributed computing, and is a recipient of the Edsger W. Dijkstra Prize, recognizing some of her earliest work establishing the pillars on which every fault-tolerant system has been built for decades. She is a member of the US National Academy of Sciences and the National Academy of Engineering, and is a fellow of the American Academy of Arts and Sciences.