AIBearisharXiv – CS AI · 9h ago7/10
🧠
On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
Researchers demonstrate significant privacy vulnerabilities in tabular diffusion models (TDMs), which are increasingly used to generate synthetic data as privacy-preserving alternatives. Through membership inference attacks in both black-box and white-box settings, the study reveals that attackers can successfully breach these systems without perfect knowledge of training data or massive computational resources, while also exposing flaws in commonly-used privacy metrics.