Attention layers in tabular foundation models enable effective membership inference attacks via pattern concentration, addressed by an inference-time k-anonymity defense on high-risk queries that cuts leakage by ~50% with minimal utility loss.
Sok: Challenges in tabular membership inference attacks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries
Attention layers in tabular foundation models enable effective membership inference attacks via pattern concentration, addressed by an inference-time k-anonymity defense on high-risk queries that cuts leakage by ~50% with minimal utility loss.