# Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks

arXiv: https://arxiv.org/abs/2102.05975 · HTML: https://mlsanity.com/paper/2102.05975/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 11 Feb 2021.

## Builds on (most cited first, 10 of 10)

- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [A comparative study of fairness-enhancing interventions in machine learning](https://mlsanity.com/paper/1802.04422/) (2018)
- [A General Approach to Adding Differential Privacy to Iterative Training Procedures](https://mlsanity.com/paper/1812.06210/) (2018)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligence](https://mlsanity.com/paper/2008.01916/) (2020)
- [Differentially Private and Fair Classification via Calibrated Functional Mechanism](https://mlsanity.com/paper/2001.04958/) (2020)
- [Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning](https://mlsanity.com/paper/2008.08807/) (2020)
- [Evaluation of Fairness Trade-offs in Predicting Student Success](https://mlsanity.com/paper/2007.00088/) (2020)
- [Correspondences between Privacy and Nondiscrimination: Why They Should Be Studied Together](https://mlsanity.com/paper/1808.01735/) (2018)

## Built on by (most cited first, 17 of 17)

- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey](https://mlsanity.com/paper/2310.01424/) (2023)
- [A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications](https://mlsanity.com/paper/2308.16375/) (2023)
- [Differentially Private Counterfactuals via Functional Mechanism](https://mlsanity.com/paper/2208.02878/) (2022)
- [The Impact of Differential Privacy on Group Disparity Mitigation](https://mlsanity.com/paper/2203.02745/) (2022)
- [Cooperative Multi-Agent Fairness and Equivariant Policies](https://mlsanity.com/paper/2106.05727/) (2021)
- [Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond](https://mlsanity.com/paper/2503.07501/) (2025)
- [Hierarchical Federated Learning with Privacy](https://mlsanity.com/paper/2206.05209/) (2022)
- [FairDP: Certified Fairness with Differential Privacy](https://mlsanity.com/paper/2305.16474/) (2023)
- [Holistic Survey of Privacy and Fairness in Machine Learning](https://mlsanity.com/paper/2307.15838/) (2023)
- [On the Fairness ROAD: Robust Optimization for Adversarial Debiasing](https://mlsanity.com/paper/2310.18413/) (2023)
- [Engineering the Law-Machine Learning Translation Problem: Developing Legally Aligned Models](https://mlsanity.com/paper/2504.16969/) (2025)
- [Automated discovery of trade-off between utility, privacy and fairness in machine learning models](https://mlsanity.com/paper/2311.15691/) (2023)
- [Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models](https://mlsanity.com/paper/2308.08774/) (2023)
- [Responsible Emergent Multi-Agent Behavior](https://mlsanity.com/paper/2311.01609/) (2023)
- [Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling](https://mlsanity.com/paper/2604.27598/) (2026)
- [Balancing Fairness, Privacy, and Accuracy: A Multitask Adversarial Framework for Centralized Data-Driven Systems](https://mlsanity.com/paper/2605.24458/) (2026)

## Abstract (arXiv)

To enable an ethical and legal use of machine learning algorithms, they must both be fair and protect the privacy of those whose data are being used. However, implementing privacy and fairness constraints might come at the cost of utility (Jayaraman & Evans, 2019; Gong et al., 2020). This paper investigates the privacy-utility-fairness trade-off in neural networks by comparing a Simple (S-NN), a Fair (F-NN), a Differentially Private (DP-NN), and a Differentially Private and Fair Neural Network (DPF-NN) to evaluate differences in performance on metrics for privacy (epsilon, delta), fairness (risk difference), and utility (accuracy). In the scenario with the highest considered privacy guarantees (epsilon = 0.1, delta = 0.00001), the DPF-NN was found to achieve better risk difference than all the other neural networks with only a marginally lower accuracy than the S-NN and DP-NN. This model is considered fair as it achieved a risk difference below the strict (0.05) and lenient (0.1) thresholds. However, while the accuracy of the proposed model improved on previous work from Xu, Yuan and Wu (2019), the risk difference was found to be worse.