Evaluating the Fairness Impact of Differentially Private Synthetic Data

05/09/2022
by   Blake Bullwinkel, et al.
0

Differentially private (DP) synthetic data is a promising approach to maximizing the utility of data containing sensitive information. Due to the suppression of underrepresented classes that is often required to achieve privacy, however, it may be in conflict with fairness. We evaluate four DP synthesizers and present empirical results indicating that three of these models frequently degrade fairness outcomes on downstream binary classification tasks. We draw a connection between fairness and the proportion of minority groups present in the generated synthetic data, and find that training synthesizers on data that are pre-processed via a multi-label undersampling method can promote more fair outcomes without degrading accuracy.

READ FULL TEXT
research
06/15/2021

An Analysis of the Deployment of Models Trained on Private Tabular Synthetic Data: Unexpected Surprises

Diferentially private (DP) synthetic datasets are a powerful approach fo...
research
06/02/2023

Harnessing large-language models to generate private synthetic text

Differentially private (DP) training methods like DP-SGD can protect sen...
research
04/27/2022

Spending Privacy Budget Fairly and Wisely

Differentially private (DP) synthetic data generation is a practical met...
research
06/30/2023

FFPDG: Fast, Fair and Private Data Generation

Generative modeling has been used frequently in synthetic data generatio...
research
05/24/2023

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Generating differentially private (DP) synthetic data that closely resem...
research
10/17/2022

Stochastic Differentially Private and Fair Learning

Machine learning models are increasingly used in high-stakes decision-ma...
research
07/07/2023

Programmable Synthetic Tabular Data Generation

Large amounts of tabular data remain underutilized due to privacy, data ...

Please sign up or login with your details

Forgot password? Click here to reset