FERMI improves membership inference on tabular diffusion models by mapping relational auxiliary information into attack features, raising TPR at 0.1 FPR by up to 53% white-box and 22% black-box over single-table baselines.
Scalable membership inference attacks via quantile regression.Advances in Neural Information Processing Systems, 36:314–330
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models
FERMI improves membership inference on tabular diffusion models by mapping relational auxiliary information into attack features, raising TPR at 0.1 FPR by up to 53% white-box and 22% black-box over single-table baselines.