When acting as a privacy-enhancing technology, synthetic data generation (SDG) aims to maintain a resemblance to the real data while excluding personally-identifiable information. Many SDG algorithms provide robust differential privacy (DP) guarantees to this end. However, we show that the strongest class of SDG algorithms--those that preserve \textit{marginal probabilities}, or similar statistics, from the underlying data--leak information about individuals that can be recovered more efficiently than previously understood. We demonstrate this by presenting a novel membership inference attack, MAMA-MIA, and evaluate it against three seminal DP SDG algorithms: MST, PrivBayes, and Private-GSD. MAMA-MIA leverages knowledge of which SDG algorithm was used, allowing it to learn information about the hidden data more accurately, and orders-of-magnitude faster, than other leading attacks. We use MAMA-MIA to lend insight into existing SDG vulnerabilities. Our approach went on to win the first SNAKE (SaNitization Algorithm under attacK ... ) competition.
View on arXiv@article{golob2025_2410.05506,
title={ Privacy Vulnerabilities in Marginals-based Synthetic Data },
author={ Steven Golob and Sikha Pentyala and Anuar Maratkhan and Martine De Cock },
journal={arXiv preprint arXiv:2410.05506},
year={ 2025 }
}