AI RESEARCH

FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models

arXiv CS.LG

ArXi:2605.11527v1 Announce Type: new Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect privacy has become a pressing question. Membership inference attacks are the standard tool for this purpose, yet existing attacks assume a single-table setting and ignore the multi-relational structure of real sensitive data.