SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI

TL;DR

SAFES is a novel data synthesis framework that sequentially integrates differential privacy and fairness-aware preprocessing, enabling flexible trade-offs and improving fairness in synthetic data without substantial utility loss.

Contribution

It introduces SAFES, a generalizable sequential approach combining privacy and fairness in data synthesis, addressing limitations of prior methods that focus on single tasks or lack flexibility.

Findings

SAFES improves fairness metrics significantly.

Synthetic data maintains high utility under reasonable privacy.

Flexible privacy-fairness-utility trade-offs are achievable.

Abstract

As data-driven and AI-based decision making gains widespread adoption across disciplines, it is crucial that both data privacy and decision fairness are appropriately addressed. Although differential privacy (DP) provides a robust framework for guaranteeing privacy and methods are available to improve fairness, most prior work treats the two concerns separately. Even though there are existing approaches that consider privacy and fairness simultaneously, they typically focus on a single specific learning task, limiting their generalizability. In response, we introduce SAFES, a Sequential PrivAcy and Fairness Enhancing data Synthesis procedure that sequentially combines DP data synthesis with a fairness-aware data preprocessing step. SAFES allows users flexibility in navigating the privacy-fairness-utility trade-offs. We illustrate SAFES with different DP synthesizers and fairness-aware data preprocessing methods and run extensive experiments on multiple real datasets to examine the privacy-fairness-utility trade-offs of synthetic data generated by SAFES. Empirical evaluations demonstrate that for reasonable privacy loss, SAFES-generated synthetic data can achieve significantly improved fairness metrics with relatively low utility loss.