# Disparate Impact in Differential Privacy from Gradient Misalignment

arXiv: https://arxiv.org/abs/2206.07737 · HTML: https://mlsanity.com/paper/2206.07737/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 24 of 24)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [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)
- [Understanding Gradient Clipping in Private SGD: A Geometric Perspective](https://mlsanity.com/paper/2006.15429/) (2020)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [AdaCliP: Adaptive Clipping for Private SGD](https://mlsanity.com/paper/1908.07643/) (2019)
- [Differentially Private Fair Learning](https://mlsanity.com/paper/1812.02696/) (2018)
- [Differentially Private Model Publishing for Deep Learning](https://mlsanity.com/paper/1904.02200/) (2019)
- [Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy](https://mlsanity.com/paper/2009.06389/) (2020)
- [Fair Decision Making using Privacy-Protected Data](https://mlsanity.com/paper/1905.12744/) (2019)
- [Decentralized Federated Learning through Proxy Model Sharing](https://mlsanity.com/paper/2111.11343/) (2021)
- [Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach](https://mlsanity.com/paper/2009.12562/) (2020)
- [Fair Learning with Private Demographic Data](https://mlsanity.com/paper/2002.11651/) (2020)
- [CaPC Learning: Confidential and Private Collaborative Learning](https://mlsanity.com/paper/2102.05188/) (2021)
- [Privacy Enhanced Multimodal Neural Representations for Emotion Recognition](https://mlsanity.com/paper/1910.13212/) (2019)

## Built on by (most cited first, 30 of 31)

- [Privacy and Fairness in Federated Learning: on the Perspective of Trade-off](https://mlsanity.com/paper/2306.14123/) (2023)
- [Fair Machine Unlearning: Data Removal while Mitigating Disparities](https://mlsanity.com/paper/2307.14754/) (2023)
- [Differentially Private Learning with Per-Sample Adaptive Clipping](https://mlsanity.com/paper/2212.00328/) (2022)
- [Conformal Prediction Sets Can Cause Disparate Impact](https://mlsanity.com/paper/2410.01888/) (2024)
- [Augment then Smooth: Reconciling Differential Privacy with Certified Robustness](https://mlsanity.com/paper/2306.08656/) (2023)
- [SoK: Unintended Interactions among Machine Learning Defenses and Risks](https://mlsanity.com/paper/2312.04542/) (2023)
- [Trustworthy AI Must Account for Interactions](https://mlsanity.com/paper/2504.07170/) (2025)
- [A Closer Look at the Calibration of Differentially Private Learners](https://mlsanity.com/paper/2210.08248/) (2022)
- [Toward the Tradeoffs between Privacy, Fairness and Utility in Federated Learning](https://mlsanity.com/paper/2311.18190/) (2023)
- [Differentially Private Clustered Federated Learning](https://mlsanity.com/paper/2405.19272/) (2024)
- [PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning](https://mlsanity.com/paper/2407.15224/) (2024)
- [Regulation Games for Trustworthy Machine Learning](https://mlsanity.com/paper/2402.03540/) (2024)
- [Differentially Private Fair Binary Classifications](https://mlsanity.com/paper/2402.15603/) (2024)
- [PFGuard: A Generative Framework with Privacy and Fairness Safeguards](https://mlsanity.com/paper/2410.02246/) (2024)
- [SoK: What Makes Private Learning Unfair?](https://mlsanity.com/paper/2501.14414/) (2025)
- [Differentially Private Prototypes for Imbalanced Transfer Learning](https://mlsanity.com/paper/2406.08039/) (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)
- [Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping](https://mlsanity.com/paper/2506.01396/) (2025)
- [Enhancing DP-SGD through Non-monotonous Adaptive Scaling Gradient Weight](https://mlsanity.com/paper/2411.03059/) (2024)
- [Private Rate-Constrained Optimization with Applications to Fair Learning](https://mlsanity.com/paper/2505.22703/) (2025)
- [SoftAdaClip: A Smooth Clipping Strategy for Fair and Private Model Training](https://mlsanity.com/paper/2510.01447/) (2025)
- [Private and Fair Machine Learning: Revisiting the Disparate Impact of Differentially Private SGD](https://mlsanity.com/paper/2510.01744/) (2025)
- [On Optimal Hyperparameters for Differentially Private Deep Transfer Learning](https://mlsanity.com/paper/2510.20616/) (2025)
- [Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness](https://mlsanity.com/paper/2603.04881/) (2026)
- [On the Impact of Output Perturbation on Fairness in Binary Linear Classification](https://mlsanity.com/paper/2402.03011/) (2024)
- [Steps Adaptive Decay DPSGD: Enhancing Performance on Imbalanced Datasets with Differential Privacy with HAM10000](https://mlsanity.com/paper/2507.06619/) (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)
- [FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility](https://mlsanity.com/paper/2510.26841/) (2025)
- [Federated Learning at the Forefront of Fairness: A Multifaceted Perspective](https://mlsanity.com/paper/2602.00718/) (2026)

## Abstract (arXiv)

As machine learning becomes more widespread throughout society, aspects including data privacy and fairness must be carefully considered, and are crucial for deployment in highly regulated industries. Unfortunately, the application of privacy enhancing technologies can worsen unfair tendencies in models. In particular, one of the most widely used techniques for private model training, differentially private stochastic gradient descent (DPSGD), frequently intensifies disparate impact on groups within data. In this work we study the fine-grained causes of unfairness in DPSGD and identify gradient misalignment due to inequitable gradient clipping as the most significant source. This observation leads us to a new method for reducing unfairness by preventing gradient misalignment in DPSGD.