Synthetic Data, Similarity-based Privacy Metrics, and Regulatory (Non-)Compliance
arXiv:2407.16929v22 citationsh-index: 9
Originality Synthesis-oriented
AI Analysis
This highlights a critical flaw in privacy protection for synthetic data users, which is incremental as it critiques existing methods without proposing a new solution.
The paper argues that similarity-based privacy metrics fail to ensure regulatory compliance for synthetic data, as they do not protect against singling out and linkability and ignore the motivated intruder test.
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.