Membership Inference over Diffusion-models-based Synthetic Tabular Data
By: Peini Cheng, Amir Bahmani
Potential Business Impact:
Protects private data when making fake data.
This study investigates the privacy risks associated with diffusion-based synthetic tabular data generation methods, focusing on their susceptibility to Membership Inference Attacks (MIAs). We examine two recent models, TabDDPM and TabSyn, by developing query-based MIAs based on the step-wise error comparison method. Our findings reveal that TabDDPM is more vulnerable to these attacks. TabSyn exhibits resilience against our attack models. Our work underscores the importance of evaluating the privacy implications of diffusion models and encourages further research into robust privacy-preserving mechanisms for synthetic data generation.
Similar Papers
Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesis
Machine Learning (CS)
Finds hidden data secrets in fake information.
MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
Cryptography and Security
Finds if private data was used to make fake data.
Ensembling Membership Inference Attacks Against Tabular Generative Models
Cryptography and Security
Finds if fake data reveals real secrets.