Tax returns and financial filings, health records, education records, and crime data are just some of detailed and highly sensitive data that governments have about people. Businesses also have huge archives of sensitive data, including consumer purchases, cellphone mobility traces, and video surveillance.
Today a tiny fraction of these data are released as open data or sold as de-identified data. The rest are locked up, unable to benefit society or promote new economic activity. Worse, much of that allegedly de-identified data can actually be re-identified.
Privacy Enhancing Technologies (PETs) use advanced mathematics and computational techniques to let organizations analyze and publish sensitive data while protecting the privacy or individuals and sensitive data from organizations. Although these techniques have existed for decades, they are increasingly being deployed by governments and businesses.
In this AI Cyber Lunch, Simson Garfinkel, Chief Scientist of BasisTech, LLC and Visiting Lecturer at Harvard Univeristy, will present the case for PETs, explains popular PETs for a non-technical audience, and discusses the specific controversy of deploying differential privacy for the 2020 US Census.
Q&A to follow. Buffet-style lunch will be served.
Registration: RSVP required. A Harvard University ID is required for in-person attendance. All are welcome to attend on Zoom.
Recording: This seminar will NOT be recorded.
Accessibility: To request accommodations or who have questions about access, please contact Liz Hanlon (ehanlon@hks.harvard.edu) in advance of the session.
Full Abstract
Tax returns and financial filings, health records, education records, and crime data are just some of detailed and highly sensitive data that governments have about people.
Businesses also have huge archives of sensitive data, including consumer purchases, cellphone mobility traces, and video surveillance.
Today a tiny fraction of these data are released as open data or sold as de-identified data. The rest are locked up, unable to benefit society or promote new economic activity. Worse, much of that allegedly de-identified data can actually be re-identified, as happened when journalists at The Pillar used de-identified data to identify Catholic priests who were going to gay bars and using hookup apps.
Privacy Enhancing Technologies (PETs) use advanced mathematics and computational techniques to let organizations analyze and publish sensitive data while protecting the privacy or individuals and sensitive data from organizations. Although these techniques have existed for decades, they are increasingly being deployed by governments and businesses.
PETs are not without controversy: when the US Census Bureau adopted a PET called differential privacy for the 2020 Census, more than 4000 academics signed an open letter voicing their opposition: they were concerned that differential privacy would do such a good job protecting privacy that the resulting data would be useless for academic research.
This talk presents the case for PETs, explains popular PETs for a non-technical audience, and discusses the specific controversy of deploying differential privacy for the 2020 US Census.
About the Speaker
Dr. Simson Garfinkel (former Senior Computer Scientist for Confidentiality and Data Access, US Census Bureau) is the Chief Scientist of BasisTech, LLC., a technology accelerator in Somerville Massachusetts, and a Visiting Lecturer at Harvard University, where he co-teaches "AC221: Critical Thinking in Data Science," an advanced course about data science ethics. Dr. Garfinkel also held a senior technical position for the Chief Data Officer at the US Department of Homeland Security.
Dr. Garfinkel's 18th book, Differential Privacy, will be published in March 2025 by MIT Press. His last book, Law and Policy for the Quantum Age, was published in 2021 by Cambridge University Press. Both books are open access.
