Date: February 26, 2018
Time: 11:45 AM - 1:05 PM
Location: Room E404, CSE Building
Host: UF CISE Department
Admission: This event is free and open to the public.
Privacy-Preserving Data Synthesis and Inference Attacks
Abstract: A challenging problem in data privacy is privacy-preserving data publishing. Straightforward approaches such as removing identifiers to ensure anonymity do not provide meaningful protection against inference attacks.
In this talk, I will describe a new framework to share sensitive datasets in a privacy-preserving way. I will show how to construct a mechanism to synthesize full data records using a probabilistic generative model. A key feature of this technique is that privacy is not achieved by modifying the generative model or adding noise. Instead, a privacy test is used to decide whether each synthesized record can safely be published. On the theoretical front, I will show that appropriately randomizing the privacy test yields differential privacy. On the experimental front, I will apply the framework to various types of data, including census microdata, location trajectories, and images.
Biography: Vincent Bindschaedler is currently a Ph.D. candidate in Computer Science at the University of Illinois at Urbana-Champaign (UIUC). He received his M.S. and B.S. from EPFL. His research interests include data privacy and applied cryptography. His recent work focuses on privacy-preserving data sharing and understanding side-channels threats.