TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Data
This addresses privacy concerns for data sharers and users by providing tools to evaluate synthetic data, but it is incremental as it builds on prior attack methods.
The authors tackled the problem of insufficient privacy protection in synthetic data by introducing TAPAS, a toolbox of attacks for auditing privacy, which includes generalizations of prior works and novel attacks, and they demonstrated it on several examples.
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.