SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI
ACM Transactions on Probabilistic Machine Learning · 2025
DOI: 10.1145/3777907 ↗At a glance
Journal article in ACM Transactions on Probabilistic Machine Learning, 2025. Written by Spencer Giddens and 2 co-authors. 70 references.
Abstract (original language)
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 S equential Priv A cy and F airness E nhancing data S ynthesis 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.
Cite
APA
Giddens, S., Lang, X., & Liu, F. (2025). SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI. ACM Transactions on Probabilistic Machine Learning. https://doi.org/10.1145/3777907
Vancouver
Giddens S, Lang X, Liu F. SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI. ACM Transactions on Probabilistic Machine Learning. 2025. doi:10.1145/3777907
BibTeX
@article{Giddens2025,
author = {Giddens, Spencer and Lang, Xiaoan and Liu, Fang},
title = {SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI},
journal = {ACM Transactions on Probabilistic Machine Learning},
year = {2025},
doi = {10.1145/3777907}
}
EUVIMED