ISTA Lecture Cynthia Dwork
Differential Privacy: Public Methods for Private Data
Differential privacy is a mathematically rigorous definition of privacy tailored to the statistical analysis of large datasets. Simple aggregate statistics of confidential data always leak some information. Each of those statistics is like a small x-ray: An individual exposure causes little damage, but, just as risk from x-rays accumulates to cause serious physical harm, information leakage due to multiple statistics can in combination completely destroy privacy. Differential privacy provides a quantitative measure of privacy loss and mathematics for how it accumulates. Equipped with this measure, researchers and practitioners design methods to control privacy loss, just as algorithms experts and programmers design methods to minimize the running time of their programs.
Differential Privacy is now widely deployed in industry. In the public sphere, Differential Privacy most notably served as the foundation for the confidentiality protections legally required in the 2020 US Decennial Census. For the first time, this allowed complete transparency regarding the Census Bureau’s privacy-preserving methods, enabling the publication of a detailed description of the algorithm and the GitHub codebase.
This talk will explain the Differential Privacy guarantee, give some intuition about how to achieve it, and discuss its uses in industry and government.
A reception with food and drinks will be available for all registered guest after the lecture, free of charge.
🗓️ December 10, 2025
🕔 5 - 6 pm
📍 Institute of Science and Technology Austria (ISTA)
🚍 Shuttle bus from Heiligenstadt
Register for free here:
https://pretix.eu/ista-events/ista-lecture-dwork/
Also check out other Nonprofit events in Klosterneuburg .
