Contrastive Learning-Based privacy metrics in Tabular Synthetic Datasets

TL;DR

This paper introduces a contrastive learning-based approach to improve privacy metrics for synthetic tabular datasets, enabling more effective and intuitive privacy assessments in sensitive sectors like healthcare and finance.

Contribution

It proposes a novel contrastive embedding method that enhances privacy evaluation by unifying similarity and attack-based metrics for tabular data.

Findings

Contrastive embeddings improve privacy metric performance.

Simple metrics can match advanced GDPR-compliant methods.

The approach is efficient and easy to implement.

Abstract

Synthetic data has garnered attention as a Privacy Enhancing Technology (PET) in sectors such as healthcare and finance. When using synthetic data in practical applications, it is important to provide protection guarantees. In the literature, two family of approaches are proposed for tabular data: on the one hand, Similarity-based methods aim at finding the level of similarity between training and synthetic data. Indeed, a privacy breach can occur if the generated data is consistently too similar or even identical to the train data. On the other hand, Attack-based methods conduce deliberate attacks on synthetic datasets. The success rates of these attacks reveal how secure the synthetic datasets are. In this paper, we introduce a contrastive method that improves privacy assessment of synthetic datasets by embedding the data in a more representative space. This overcomes obstacles surrounding the multitude of data types and attributes. It also makes the use of intuitive distance metrics possible for similarity measurements and as an attack vector. In a series of experiments with publicly available datasets, we compare the performances of similarity-based and attack-based methods, both with and without use of the contrastive learning-based embeddings. Our results show that relatively efficient, easy to implement privacy metrics can perform equally well as more advanced metrics explicitly modeling conditions for privacy referred to by the GDPR.