Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ward, Joshua, Wang, Chi-Hua, Cheng, Guang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917699359080448
author Ward, Joshua
Wang, Chi-Hua
Cheng, Guang
author_facet Ward, Joshua
Wang, Chi-Hua
Cheng, Guang
contents The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. In evaluating these models, a variety of methods have been proposed to measure the tendency to copy data from the training dataset when generating a sample. However, these methods suffer from either not considering data-copying from a privacy threat perspective, not being motivated by recent results in the data-copying literature or being difficult to make compatible with the high dimensional, mixed type nature of tabular data. This paper proposes a new similarity metric and Membership Inference Attack called Data Plagiarism Index (DPI) for tabular data. We show that DPI evaluates a new intuitive definition of data-copying and characterizes the corresponding privacy risk. We show that the data-copying identified by DPI poses both privacy and fairness threats to common, high performing architectures; underscoring the necessity for more sophisticated generative modeling techniques to mitigate this issue.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13012
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models
Ward, Joshua
Wang, Chi-Hua
Cheng, Guang
Machine Learning
Cryptography and Security
The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. In evaluating these models, a variety of methods have been proposed to measure the tendency to copy data from the training dataset when generating a sample. However, these methods suffer from either not considering data-copying from a privacy threat perspective, not being motivated by recent results in the data-copying literature or being difficult to make compatible with the high dimensional, mixed type nature of tabular data. This paper proposes a new similarity metric and Membership Inference Attack called Data Plagiarism Index (DPI) for tabular data. We show that DPI evaluates a new intuitive definition of data-copying and characterizes the corresponding privacy risk. We show that the data-copying identified by DPI poses both privacy and fairness threats to common, high performing architectures; underscoring the necessity for more sophisticated generative modeling techniques to mitigate this issue.
title Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2406.13012