# Auditing Fairness-Privacy Trade-offs: Subpopulation-Level Effects of Fairness-Enhancing Algorithms

arXiv: https://arxiv.org/abs/2607.14607 · HTML: https://mlsanity.com/paper/2607.14607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [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)
- [ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning](https://mlsanity.com/paper/2007.09339/) (2020)
- [Fairness via Representation Neutralization](https://mlsanity.com/paper/2106.12674/) (2021)
- [Diffprivlib: The IBM Differential Privacy Library](https://mlsanity.com/paper/1907.02444/) (2019)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Disparate Vulnerability to Membership Inference Attacks](https://mlsanity.com/paper/1906.00389/) (2019)
- [Decision Making with Differential Privacy under a Fairness Lens](https://mlsanity.com/paper/2105.07513/) (2021)
- [Differential Privacy has Bounded Impact on Fairness in Classification](https://mlsanity.com/paper/2210.16242/) (2022)
- [Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability](https://mlsanity.com/paper/1911.09777/) (2019)
- [The Impact of Differential Privacy on Group Disparity Mitigation](https://mlsanity.com/paper/2203.02745/) (2022)
- [Evaluating the Fairness Impact of Differentially Private Synthetic Data](https://mlsanity.com/paper/2205.04321/) (2022)
- [A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results](https://mlsanity.com/paper/2405.14725/) (2024)
- [When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks](https://mlsanity.com/paper/2311.03865/) (2023)

## Abstract (arXiv)

Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees. While prior work has largely examined how privacy-preserving techniques affect fairness, the inverse question-how fairness-enhancing algorithms influence privacy leakage-remains underexplored. We present the first comprehensive study of how fairness interventions affect membership inference privacy risks at the subpopulation level. By adapting the Likelihood Ratio Attack (LiRA) for subgroup auditing, we uncover privacy disparities that aggregate evaluations obscure. We further analyze how Differential Privacy (DP) interacts with fairness-enhancing methods across different categories, showing that DP's privacy benefits and utility costs are unevenly distributed across subpopulations. Our results demonstrate that fairness interventions do not uniformly increase privacy risk; their impact depends on model architecture, subgroup size, and mitigation strategy. These findings reveal that fairness, privacy, and utility must be jointly evaluated at the subpopulation level, and we introduce the first unified empirical framework to support such auditing in practice.