TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic DataDownload PDF

03 Oct 2022 (modified: 29 Apr 2024)Neurips 2022 SyntheticData4MLReaders: Everyone
Keywords: Privacy, Synthetic Data, Privacy Attacks
Abstract: 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 PrivE, 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 PrivE on several examples.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2211.06550/code)
4 Replies