# Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data

arXiv: https://arxiv.org/abs/2504.21634 · HTML: https://mlsanity.com/paper/2504.21634/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 49 references that are in the map.
- First posted on arXiv 30 Apr 2025.

## Builds on (most cited first, 24 of 24)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (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)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Fairness in Criminal Justice Risk Assessments: The State of the Art](https://mlsanity.com/paper/1703.09207/) (2017)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [Synthetic Data -- Anonymisation Groundhog Day](https://mlsanity.com/paper/2011.07018/) (2020)
- [R'enyi Divergence Variational Inference](https://mlsanity.com/paper/1602.02311/) (2016)
- [Winning the NIST Contest: A scalable and general approach to differentially private synthetic data](https://mlsanity.com/paper/2108.04978/) (2021)
- [Privacy Amplification by Iteration](https://mlsanity.com/paper/1808.06651/) (2018)
- [Benchmarking Differentially Private Synthetic Data Generation Algorithms](https://mlsanity.com/paper/2112.09238/) (2021)
- [Graphical-model based estimation and inference for differential privacy](https://mlsanity.com/paper/1901.09136/) (2019)
- [Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias](https://mlsanity.com/paper/2403.07857/) (2024)
- [Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data](https://mlsanity.com/paper/2109.11429/) (2021)
- [Differentially Private Synthetic Data: Applied Evaluations and Enhancements](https://mlsanity.com/paper/2011.05537/) (2020)
- [SoK: Differential Privacies](https://mlsanity.com/paper/1906.01337/) (2019)
- [Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration](https://mlsanity.com/paper/2008.12763/) (2020)
- [Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumvention](https://mlsanity.com/paper/2405.01820/) (2024)
- [Comparative Study of Differentially Private Data Synthesis Methods](https://mlsanity.com/paper/1602.01063/) (2016)
- [Really Useful Synthetic Data -- A Framework to Evaluate the Quality of Differentially Private Synthetic Data](https://mlsanity.com/paper/2004.07740/) (2020)
- [Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems](https://mlsanity.com/paper/2409.06708/) (2024)

## Built on by (most cited first, 1 of 1)

- [Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring](https://mlsanity.com/paper/2510.23245/) (2025)

## Abstract (arXiv)

Fairness auditing of AI systems can identify and quantify biases. However, traditional auditing using real-world data raises security and privacy concerns. It exposes auditors to security risks as they become custodians of sensitive information and targets for cyberattacks. Privacy risks arise even without direct breaches, as data analyses can inadvertently expose confidential information. To address these, we propose a framework that leverages differentially private synthetic data to audit the fairness of AI systems. By applying privacy-preserving mechanisms, it generates synthetic data that mirrors the statistical properties of the original dataset while ensuring privacy. This method balances the goal of rigorous fairness auditing and the need for strong privacy protections. Through experiments on real datasets like Adult, COMPAS, and Diabetes, we compare fairness metrics of synthetic and real data. By analyzing the alignment and discrepancies between these metrics, we assess the capacity of synthetic data to preserve the fairness properties of real data. Our results demonstrate the framework's ability to enable meaningful fairness evaluations while safeguarding sensitive information, proving its applicability across critical and sensitive domains.