Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
Researchers have introduced a statistical framework for auditing privacy in synthetic data, capable of distinguishing true disclosures from phantom ones using hypothesis testing. The method requires only synthetic outputs and a held-out control set—no model access, canary insertion, or reference model training. It is model-agnostic and provides tighter empirical lower bounds on privacy leakage than previous data-based auditing methods, while being more resource-efficient.
Why it matters: This framework enables practical and efficient detection of privacy leaks in synthetic data, addressing a key safety concern in generative AI without requiring access to the underlying model.
Full story at: arXiv Statistical ML ↗