# FairDP: Certified Fairness with Differential Privacy

arXiv: https://arxiv.org/abs/2305.16474 · HTML: https://mlsanity.com/paper/2305.16474/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 74 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (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)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Scalable Private Learning with PATE](https://mlsanity.com/paper/1802.08908/) (2018)
- [Private Stochastic Convex Optimization with Optimal Rates](https://mlsanity.com/paper/1908.09970/) (2019)
- [A Theory of Usable Information Under Computational Constraints](https://mlsanity.com/paper/2002.10689/) (2020)
- [Private Stochastic Convex Optimization: Optimal Rates in Linear Time](https://mlsanity.com/paper/2005.04763/) (2020)
- [Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks](https://mlsanity.com/paper/2002.10553/) (2020)
- [Fairness Under Unawareness: Assessing Disparity When Protected Class Is Unobserved](https://mlsanity.com/paper/1811.11154/) (2018)
- [Fairness risk measures](https://mlsanity.com/paper/1901.08665/) (2019)
- [Automated Experiments on Ad Privacy Settings: A Tale of Opacity, Choice, and Discrimination](https://mlsanity.com/paper/1408.6491/) (2014)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Learning Certified Individually Fair Representations](https://mlsanity.com/paper/2002.10312/) (2020)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Fair Learning with Private Demographic Data](https://mlsanity.com/paper/2002.11651/) (2020)
- [Controllable Guarantees for Fair Outcomes via Contrastive Information Estimation](https://mlsanity.com/paper/2101.04108/) (2021)
- [Pruning has a disparate impact on model accuracy](https://mlsanity.com/paper/2205.13574/) (2022)
- [Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning](https://mlsanity.com/paper/1709.05750/) (2017)
- [Decision Making with Differential Privacy under a Fairness Lens](https://mlsanity.com/paper/2105.07513/) (2021)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [How unfair is private learning ?](https://mlsanity.com/paper/2206.03985/) (2022)
- [Differential Privacy has Bounded Impact on Fairness in Classification](https://mlsanity.com/paper/2210.16242/) (2022)
- [Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks](https://mlsanity.com/paper/2102.05975/) (2021)
- [Stochastic Differentially Private and Fair Learning](https://mlsanity.com/paper/2210.08781/) (2022)
- [Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness](https://mlsanity.com/paper/1906.01444/) (2019)
- [What You See is What You Get: Principled Deep Learning via Distributional Generalization](https://mlsanity.com/paper/2204.03230/) (2022)

## Built on by (most cited first, 4 of 4)

- [Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping](https://mlsanity.com/paper/2506.01396/) (2025)
- [Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification](https://mlsanity.com/paper/2511.18876/) (2025)
- [INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy](https://mlsanity.com/paper/2605.07930/) (2026)
- [Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems](https://mlsanity.com/paper/2605.24458/) (2026)

## Abstract (arXiv)

This paper introduces FairDP, a novel training mechanism designed to provide group fairness certification for the trained model's decisions, along with a differential privacy (DP) guarantee to protect training data. The key idea of FairDP is to train models for distinct individual groups independently, add noise to each group's gradient for data privacy protection, and progressively integrate knowledge from group models to formulate a comprehensive model that balances privacy, utility, and fairness in downstream tasks. By doing so, FairDP ensures equal contribution from each group while gaining control over the amount of DP-preserving noise added to each group's contribution. To provide fairness certification, FairDP leverages the DP-preserving noise to statistically quantify and bound fairness metrics. An extensive theoretical and empirical analysis using benchmark datasets validates the efficacy of FairDP and improved trade-offs between model utility, privacy, and fairness compared with existing methods. Our empirical results indicate that FairDP can improve fairness metrics by more than 65% on average while attaining marginal utility drop (less than 4% on average) under a rigorous DP-preservation across benchmark datasets compared with existing baselines.