MIA-EPT: Membership Inference Attack
via Error Prediction for Tabular Data

1Ben-Gurion University of the Negev
*Equal contribution

Accepted to the AAAI’26 Workshop on Shaping Responsible Synthetic Data in the Era of Foundation Models (RSD).

MIA-EPT teaser figure (placeholder)

Abstract

MIA-EPT is a novel black-box membership inference attack designed for tabular diffusion models. It constructs error-based feature vectors by masking and reconstructing attributes of target records, and infers membership from how well attributes can be predicted using only the released synthetic data.

We validate MIA-EPT across multiple diffusion-based synthesizers, achieving AUC-ROC up to 0.599 and TPR@10% FPR up to 22.0% in internal tests, and 2nd place in the MIDST 2025 Black-box Multi-Table track (TPR@10% FPR = 20.0%).

Method Overview

MIA-EPT follows a shadow-model pipeline: train shadow diffusion models, train per-column attribute predictors on synthetic data, extract structured error profiles for records, and train an attack classifier to predict membership.

MIA-EPT pipeline (placeholder for Figure 1)

Results

We evaluate MIA-EPT on diffusion-based tabular synthesizers (including single-table and multi-table settings) and report AUC-ROC and TPR@10% FPR, matching the MIDST competition operating point.

ROC with zoom — TabDDPM comparison ROC with zoom — ClavaDDPM comparison

Top-line Metrics (quick view)

Setting Metric Value
Internal evaluation Best AUC-ROC 0.599
Internal evaluation Best TPR@10% FPR 22.0%
MIDST 2025 (Black-box Multi-Table) TPR@10% FPR 20.0% (2nd place)

MIDST Competition

MIA-EPT achieved 2nd place in the MIDST 2025 Black-box Multi-Table track (TPR@10% FPR = 20.0%), demonstrating measurable membership leakage in diffusion-based synthetic tabular data.

BibTeX

@misc{german2025mia_ept,
  title        = {MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data},
  author       = {Eyal German and Daniel Samira and Yuval Elovici and Asaf Shabtai},
  year         = {2025},
  eprint       = {2509.13046},
  archivePrefix= {arXiv},
  primaryClass = {cs.CR},
  url          = {https://arxiv.org/abs/2509.13046}
}