Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance

Abstract

In this paper, we argue that similarity-based privacy metrics cannot ensure regulatory compliance of synthetic data. Our analysis and counter-examples show that they do not protect against singling out and linkability and, among other fundamental issues, completely ignore the motivated intruder test.

arXiv commentAccepted to the 2nd Workshop on Generative AI and Law (GenLaw 2024), part of ICML 2024