Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meeus, Matthieu, Guépin, Florent, Cretu, Ana-Maria, de Montjoye, Yves-Alexandre
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929238018359296
author Meeus, Matthieu
Guépin, Florent
Cretu, Ana-Maria
de Montjoye, Yves-Alexandre
author_facet Meeus, Matthieu
Guépin, Florent
Cretu, Ana-Maria
de Montjoye, Yves-Alexandre
contents Synthetic data is seen as the most promising solution to share individual-level data while preserving privacy. Shadow modeling-based Membership Inference Attacks (MIAs) have become the standard approach to evaluate the privacy risk of synthetic data. While very effective, they require a large number of datasets to be created and models trained to evaluate the risk posed by a single record. The privacy risk of a dataset is thus currently evaluated by running MIAs on a handful of records selected using ad-hoc methods. We here propose what is, to the best of our knowledge, the first principled vulnerable record identification technique for synthetic data publishing, leveraging the distance to a record's closest neighbors. We show our method to strongly outperform previous ad-hoc methods across datasets and generators. We also show evidence of our method to be robust to the choice of MIA and to specific choice of parameters. Finally, we show it to accurately identify vulnerable records when synthetic data generators are made differentially private. The choice of vulnerable records is as important as more accurate MIAs when evaluating the privacy of synthetic data releases, including from a legal perspective. We here propose a simple yet highly effective method to do so. We hope our method will enable practitioners to better estimate the risk posed by synthetic data publishing and researchers to fairly compare ever improving MIAs on synthetic data.
format Preprint
id arxiv_https___arxiv_org_abs_2306_10308
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing
Meeus, Matthieu
Guépin, Florent
Cretu, Ana-Maria
de Montjoye, Yves-Alexandre
Cryptography and Security
Artificial Intelligence
Synthetic data is seen as the most promising solution to share individual-level data while preserving privacy. Shadow modeling-based Membership Inference Attacks (MIAs) have become the standard approach to evaluate the privacy risk of synthetic data. While very effective, they require a large number of datasets to be created and models trained to evaluate the risk posed by a single record. The privacy risk of a dataset is thus currently evaluated by running MIAs on a handful of records selected using ad-hoc methods. We here propose what is, to the best of our knowledge, the first principled vulnerable record identification technique for synthetic data publishing, leveraging the distance to a record's closest neighbors. We show our method to strongly outperform previous ad-hoc methods across datasets and generators. We also show evidence of our method to be robust to the choice of MIA and to specific choice of parameters. Finally, we show it to accurately identify vulnerable records when synthetic data generators are made differentially private. The choice of vulnerable records is as important as more accurate MIAs when evaluating the privacy of synthetic data releases, including from a legal perspective. We here propose a simple yet highly effective method to do so. We hope our method will enable practitioners to better estimate the risk posed by synthetic data publishing and researchers to fairly compare ever improving MIAs on synthetic data.
title Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2306.10308