Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Andrey, Paul, Bars, Batiste Le, Tommasi, Marc
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.00758
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909898885824512
author Andrey, Paul
Bars, Batiste Le
Tommasi, Marc
author_facet Andrey, Paul
Bars, Batiste Le
Tommasi, Marc
contents Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on graphical models. This attack builds upon MAMA-MIA, a recently-published state-of-the-art method. It lowers its computational cost and requires less attacker knowledge. Our attack is the product of a two-fold improvement. First, we recover the graphical model having generated a synthetic dataset by using solely that dataset, rather than shadow-modeling over an auxiliary one. This proves less costly and more performant. Second, we introduce a more mathematically-grounded attack score, that provides a natural threshold for binary predictions. In our experiments, TAMIS achieves better or similar performance as MAMA-MIA on replicas of the SNAKE challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00758
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TAMIS: Tailored Membership Inference Attacks on Synthetic Data
Andrey, Paul
Bars, Batiste Le
Tommasi, Marc
Machine Learning
Membership Inference Attacks (MIA) enable to empirically assess the privacy of a machine learning algorithm. In this paper, we propose TAMIS, a novel MIA against differentially-private synthetic data generation methods that rely on graphical models. This attack builds upon MAMA-MIA, a recently-published state-of-the-art method. It lowers its computational cost and requires less attacker knowledge. Our attack is the product of a two-fold improvement. First, we recover the graphical model having generated a synthetic dataset by using solely that dataset, rather than shadow-modeling over an auxiliary one. This proves less costly and more performant. Second, we introduce a more mathematically-grounded attack score, that provides a natural threshold for binary predictions. In our experiments, TAMIS achieves better or similar performance as MAMA-MIA on replicas of the SNAKE challenge.
title TAMIS: Tailored Membership Inference Attacks on Synthetic Data
topic Machine Learning
url https://arxiv.org/abs/2504.00758