Marcel Neunhoeffer
Marcel Neunhoeffer is a Postdoctoral Researcher at the Statistical Methods Unit of the Institute for Employment Research (IAB) in Nuremberg, Germany, and at SODA Lab at LMU Munich.
His research focuses on privacy-preserving AI and synthetic data generation.
He collaborated with the US Census Bureau and the German Federal Statistical Office (Destatis) on the development of privacy-preserving synthetic data for sensitive administrative datasets. He has published in leading venues across disciplines, including ICLR, PNAS, the Harvard Data Science Review, and Political Analysis.
As a co-founder and contributor to zweitstimme.org, he co-built a platform that communicates scientific election forecasts for German Federal elections to a broad audience, covered by major German media, including Süddeutsche Zeitung, Zeit Online, Tagesspiegel, and the Washington Post.
Session
Data analysis and machine learning often involve sensitive information. But how can we ensure that our analyses and releases do not inadvertently reveal information about the individuals in our data? Traditional approaches such as anonymization or releasing only aggregate statistics have repeatedly proven insufficient.
Differential privacy is a mathematical framework that offers provable privacy guarantees while still enabling useful data analysis. In this tutorial, we provide a hands-on introduction to differential privacy, covering key concepts relevant to understanding and applying it in practice. The focus will be on practical implementation rather than underlying theory.
Using interactive examples in Python, we will explore the core ideas of differential privacy, highlight its attractive properties and limitations, and demonstrate how to build privacy-preserving analyses using OpenDP, an open-source Python library for differential privacy. Participants will leave equipped to continue exploring differential privacy on their own. Familiarity with the basics of Python programming is helpful, but no prior knowledge of differential privacy is required.