# Differentially Private and Fair Classification via Calibrated Functional Mechanism

arXiv: https://arxiv.org/abs/2001.04958 · HTML: https://mlsanity.com/paper/2001.04958/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jan 2020.

## Built on by (most cited first, 20 of 20)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Enforcing fairness in private federated learning via the modified method of differential multipliers](https://mlsanity.com/paper/2109.08604/) (2021)
- [Pre-trained Perceptual Features Improve Differentially Private Image Generation](https://mlsanity.com/paper/2205.12900/) (2022)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [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)
- [Unraveling Privacy Risks of Individual Fairness in Graph Neural Networks](https://mlsanity.com/paper/2301.12951/) (2023)
- [Understanding Fairness Surrogate Functions in Algorithmic Fairness](https://mlsanity.com/paper/2310.11211/) (2023)
- [SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning](https://mlsanity.com/paper/2312.16191/) (2023)
- [Differentially Private Fair Binary Classifications](https://mlsanity.com/paper/2402.15603/) (2024)
- [Spending Privacy Budget Fairly and Wisely](https://mlsanity.com/paper/2204.12903/) (2022)
- [MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage](https://mlsanity.com/paper/2401.12824/) (2024)
- [Combining Machine Learning Defenses without Conflicts](https://mlsanity.com/paper/2411.09776/) (2024)
- [Learning with Differentially Private (Sliced) Wasserstein Gradients](https://mlsanity.com/paper/2502.01701/) (2025)
- [Fairly Private: Investigating The Fairness of Visual Privacy Preservation Algorithms](https://mlsanity.com/paper/2301.05012/) (2023)
- [SAFES: Sequential Privacy and Fairness Enhancing Data Synthesis for Responsible AI](https://mlsanity.com/paper/2411.09178/) (2024)
- [Stabilization of Perturbed Loss Function: Differential Privacy without Gradient Noise](https://mlsanity.com/paper/2508.15523/) (2025)
- [On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning](https://mlsanity.com/paper/2510.09114/) (2025)
- [Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems](https://mlsanity.com/paper/2605.24458/) (2026)

## Abstract (arXiv)

Machine learning is increasingly becoming a powerful tool to make decisions in a wide variety of applications, such as medical diagnosis and autonomous driving. Privacy concerns related to the training data and unfair behaviors of some decisions with regard to certain attributes (e.g., sex, race) are becoming more critical. Thus, constructing a fair machine learning model while simultaneously providing privacy protection becomes a challenging problem. In this paper, we focus on the design of classification model with fairness and differential privacy guarantees by jointly combining functional mechanism and decision boundary fairness. In order to enforce ε-differential privacy and fairness, we leverage the functional mechanism to add different amounts of Laplace noise regarding different attributes to the polynomial coefficients of the objective function in consideration of fairness constraint. We further propose an utility-enhancement scheme, called relaxed functional mechanism by adding Gaussian noise instead of Laplace noise, hence achieving (ε,δ)-differential privacy. Based on the relaxed functional mechanism, we can design (ε,δ)-differentially private and fair classification model. Moreover, our theoretical analysis and empirical results demonstrate that our two approaches achieve both fairness and differential privacy while preserving good utility and outperform the state-of-the-art algorithms.