# On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning

arXiv: https://arxiv.org/abs/2510.09114 · HTML: https://mlsanity.com/paper/2510.09114/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 22 of 22)

- [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)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [White-box vs Black-box: Bayes Optimal Strategies for Membership Inference](https://mlsanity.com/paper/1908.11229/) (2019)
- [Enhanced Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/2111.09679/) (2021)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://mlsanity.com/paper/2101.04535/) (2021)
- [A survey on datasets for fairness-aware machine learning](https://mlsanity.com/paper/2110.00530/) (2021)
- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [Privacy Auditing with One (1) Training Run](https://mlsanity.com/paper/2305.08846/) (2023)
- [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)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Disparate Vulnerability to Membership Inference Attacks](https://mlsanity.com/paper/1906.00389/) (2019)
- [Bayesian Estimation of Differential Privacy](https://mlsanity.com/paper/2206.05199/) (2022)
- [Disparate Impact in Differential Privacy from Gradient Misalignment](https://mlsanity.com/paper/2206.07737/) (2022)
- [Nearly Tight Black-Box Auditing of Differentially Private Machine Learning](https://mlsanity.com/paper/2405.14106/) (2024)
- [Differentially Private and Fair Classification via Calibrated Functional Mechanism](https://mlsanity.com/paper/2001.04958/) (2020)
- [Stochastic Differentially Private and Fair Learning](https://mlsanity.com/paper/2210.08781/) (2022)

## Abstract (arXiv)

While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups remains underexplored. Existing studies have proposed methods to assess group privacy risks, but these are based on the average-case privacy risks of data records. Such approaches may underestimate the group privacy risks, thereby potentially underestimating the disparity across group privacy risks. Moreover, the current method for assessing the worst-case privacy risks of data records is time-consuming, limiting their practical applicability. To address these limitations, we introduce a novel membership inference game that can efficiently audit the approximate worst-case privacy risks of data records. Experimental results demonstrate that our method provides a more stringent measurement of group privacy risks, yielding a reliable assessment of the disparity in group privacy risks. Furthermore, to promote privacy protection fairness in DPML, we enhance the standard DP-SGD algorithm with an adaptive group-specific gradient clipping strategy, inspired by the design of canaries in differential privacy auditing studies. Extensive experiments confirm that our algorithm effectively reduces the disparity in group privacy risks, thereby enhancing the fairness of privacy protection in DPML.