Tabular diffusion models leak membership information via attacks even with partial attacker knowledge, and common heuristic privacy metrics like distance-to-closest-record are unreliable.
Synthetic data privacy metrics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PersonaLedger LLM simulator achieves AUC 0.70 for fraud detection at epsilon=1 from DP inputs but shows significant distribution drift due to learned priors overriding input statistics on temporal and demographic features.
citing papers explorer
-
On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
Tabular diffusion models leak membership information via attacks even with partial attacker knowledge, and common heuristic privacy metrics like distance-to-closest-record are unreliable.
-
Evaluating LLM Simulators as Differentially Private Data Generators
PersonaLedger LLM simulator achieves AUC 0.70 for fraud detection at epsilon=1 from DP inputs but shows significant distribution drift due to learned priors overriding input statistics on temporal and demographic features.