# Decision Making with Differential Privacy under a Fairness Lens

arXiv: https://arxiv.org/abs/2105.07513 · HTML: https://mlsanity.com/paper/2105.07513/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 16 May 2021.

## Builds on (most cited first, 12 of 12)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [The Composition Theorem for Differential Privacy](https://mlsanity.com/paper/1311.0776/) (2013)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [Fairness in Machine Learning](https://mlsanity.com/paper/2012.15816/) (2020)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Fair Decision Making using Privacy-Protected Data](https://mlsanity.com/paper/1905.12744/) (2019)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scale](https://mlsanity.com/paper/2002.05839/) (2020)
- [Towards Practical Differential Privacy for SQL Queries](https://mlsanity.com/paper/1706.09479/) (2017)
- [Bias and Variance of Post-processing in Differential Privacy](https://mlsanity.com/paper/2010.04327/) (2020)
- [Differential Privacy of Hierarchical Census Data: An Optimization Approach](https://mlsanity.com/paper/2006.15673/) (2020)
- [An Economic Analysis of Privacy Protection and Statistical Accuracy as Social Choices](https://mlsanity.com/paper/1808.06303/) (2018)

## Built on by (most cited first, 30 of 32)

- [Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods](https://mlsanity.com/paper/2106.07153/) (2021)
- [Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey](https://mlsanity.com/paper/2202.08187/) (2022)
- [Pruning has a disparate impact on model accuracy](https://mlsanity.com/paper/2205.13574/) (2022)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?](https://mlsanity.com/paper/2106.12576/) (2021)
- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging](https://mlsanity.com/paper/2302.01622/) (2023)
- [Stochastic Differentially Private and Fair Learning](https://mlsanity.com/paper/2210.08781/) (2022)
- [A Fairness Analysis on Private Aggregation of Teacher Ensembles](https://mlsanity.com/paper/2109.08630/) (2021)
- [Post-processing of Differentially Private Data: A Fairness Perspective](https://mlsanity.com/paper/2201.09425/) (2022)
- [SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles](https://mlsanity.com/paper/2204.05157/) (2022)
- [Doubly Fair Dynamic Pricing](https://mlsanity.com/paper/2209.11837/) (2022)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?](https://mlsanity.com/paper/2111.13617/) (2021)
- [Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications](https://mlsanity.com/paper/2506.00660/) (2025)
- [Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy](https://mlsanity.com/paper/2306.06503/) (2023)
- [Trustworthy AI Must Account for Interactions](https://mlsanity.com/paper/2504.07170/) (2025)
- [On the Fairness Impacts of Private Ensembles Models](https://mlsanity.com/paper/2305.11807/) (2023)
- [FairDP: Certified Fairness with Differential Privacy](https://mlsanity.com/paper/2305.16474/) (2023)
- [Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data](https://mlsanity.com/paper/2409.19078/) (2024)
- [Crowding Out The Noise: Algorithmic Collective Action Under Differential Privacy](https://mlsanity.com/paper/2505.05707/) (2025)
- [Exploring the Unfairness of DP-SGD Across Settings](https://mlsanity.com/paper/2202.12058/) (2022)
- [Privacy and Bias Analysis of Disclosure Avoidance Systems](https://mlsanity.com/paper/2301.12204/) (2023)
- [On The Fairness Impacts of Hardware Selection in Machine Learning](https://mlsanity.com/paper/2312.03886/) (2023)
- [Fairness Issues and Mitigations in (Differentially Private) Socio-Demographic Data Processes](https://mlsanity.com/paper/2408.08471/) (2024)
- [Privacy at a Price: Exploring its Dual Impact on AI Fairness](https://mlsanity.com/paper/2404.09391/) (2024)
- [Partial sensitivity analysis in differential privacy](https://mlsanity.com/paper/2109.10582/) (2021)
- [Price-Aware Deep Learning for Electricity Markets](https://mlsanity.com/paper/2308.01436/) (2023)
- [Differentially Private Data Release on Graphs: Inefficiencies and Unfairness](https://mlsanity.com/paper/2408.05246/) (2024)
- [Optimal Allocation of Privacy Budget on Hierarchical Data Release](https://mlsanity.com/paper/2505.10871/) (2025)
- [Does Privacy Always Harm Fairness? Data-Dependent Trade-offs via Chernoff Information Neural Estimation](https://mlsanity.com/paper/2601.13698/) (2026)

## Abstract (arXiv)

Agencies, such as the U.S. Census Bureau, release data sets and statistics about groups of individuals that are used as input to a number of critical decision processes. To conform to privacy and confidentiality requirements, these agencies are often required to release privacy-preserving versions of the data. This paper studies the release of differentially private data sets and analyzes their impact on some critical resource allocation tasks under a fairness perspective. {The paper shows that, when the decisions take as input differentially private data}, the noise added to achieve privacy disproportionately impacts some groups over others. The paper analyzes the reasons for these disproportionate impacts and proposes guidelines to mitigate these effects. The proposed approaches are evaluated on critical decision problems that use differentially private census data.