Thursday, April 25
7:30pm in Bronfman Auditorium
(Wachenheim B11)
– Reception to follow –
*CS Colloquium Credit for attendance*
It’s in Your Phone. It’s in Your Browser. It’s in Your Redistricting Data! … It’s Differential Privacy.
“Anonymized data aren’t.” Either they are not really anonymized or the anonymization process destroys their utility. Aggregate statistics, too, can fail to protect privacy, sometimes spectacularly. Predictive models trained on large datasets memorize substantial portions of the training data and have been tricked into revealing this information. The US Census Bureau demonstrated a privacy attack against the statistics the Bureau itself published in 2010. Although there is provably(!) no magic bullet, Differential Privacy – a definition of privacy tailored to statistical data analysis and a collection of supporting algorithmic techniques — has proven fruitful in a wide range of settings, from generating predictive text and emoji suggestions to publication of Census redistricting data.
Why is privacy so slippery? Why is this a new problem? What is Differential Privacy, and what happened when Alabama sued to prevent its use in the 2020 Decennial redistricting data?
Cynthia Dwork, Gordon McKay Professor of Computer Science at Harvard, and Affiliated Faculty at Harvard Law School and Department of Statistics, is renowned for placing privacy-preserving data analysis on a mathematically rigorous foundation. She has also made seminal contributions in cryptography and distributed computing, and she spearheaded the investigation of the theory of algorithmic fairness, her current focus. Dwork is the recipient of numerous awards including the IEEE Hamming Medal, the RSA award for Excellence in Mathematics, the Dijkstra, G”{o}del, and Knuth Prizes, and the ACM Paris Kanellakis Theory and Practice Award. Dwork is a member of the US National Academy of Sciences and the US National Academy of Engineering, and is a Fellow of the American Academy of Arts and Sciences and the American Philosophical Society.