TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
Florimond Houssiau, James Brian Jordon, Samuel N. Cohen, Daniel, Owen, Andrew J. Elliott, James Geddes, Callum David Mole, C. Rangel-Smith, Łukasz Szpruch · arXiv (Cornell University) · 2022
Personal data collected at scale promises to improve decision-making and accelerate innovation. However, sharing and using such data raises serious privacy concerns. A promising solution is to produce synthetic data, artificial records to share instead of real data. Since synthetic records are not linked to real persons, this intuitively prevents classical re-identification attacks. However, this is insufficient to protect privacy. We here present TAPAS, a toolbox of attacks to evaluate synthetic data privacy under a wide range of scenarios. These attacks include generalizations of prior works and novel attacks. We also introduce a general framework for reasoning about privacy threats to synthetic data and showcase TAPAS on several examples.