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

arXiv: https://arxiv.org/abs/2411.09178 · HTML: https://mlsanity.com/paper/2411.09178/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Privacy-preserving tabular data synthesis, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 25 of its 74 references that are in the map.
- First posted on arXiv 14 Nov 2024.

## Placed in

- Synthetic data and self-improvement for LLMs / [Privacy-preserving tabular data synthesis](https://mlsanity.com/synth/privacy-preserving-tabular-data-synthesis/)

## Builds on (most cited first, 25 of 25)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [Winning the NIST Contest: A scalable and general approach to differentially private synthetic data](https://mlsanity.com/paper/2108.04978/) (2021)
- [AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data](https://mlsanity.com/paper/2201.12677/) (2022)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Graphical-model based estimation and inference for differential privacy](https://mlsanity.com/paper/1901.09136/) (2019)
- [A Confidence-Based Approach for Balancing Fairness and Accuracy](https://mlsanity.com/paper/1601.05764/) (2016)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data](https://mlsanity.com/paper/2109.11429/) (2021)
- [SoK: Privacy-Preserving Data Synthesis](https://mlsanity.com/paper/2307.02106/) (2023)
- [Differentially Private and Fair Classification via Calibrated Functional Mechanism](https://mlsanity.com/paper/2001.04958/) (2020)
- [Comparative Study of Differentially Private Data Synthesis Methods](https://mlsanity.com/paper/1602.01063/) (2016)
- [PreFair: Privately Generating Justifiably Fair Synthetic Data](https://mlsanity.com/paper/2212.10310/) (2022)
- [Evaluating the Fairness Impact of Differentially Private Synthetic Data](https://mlsanity.com/paper/2205.04321/) (2022)
- [Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Data](https://mlsanity.com/paper/2310.19250/) (2023)

## Abstract (arXiv)

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.