# The Impact of Generalization Techniques on the Interplay Among Privacy, Utility, and Fairness in Image Classification

arXiv: https://arxiv.org/abs/2412.11951 · HTML: https://mlsanity.com/paper/2412.11951/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 25 of 25)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [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)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Unlocking High-Accuracy Differentially Private Image Classification through Scale](https://mlsanity.com/paper/2204.13650/) (2022)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [On the Importance of Difficulty Calibration in Membership Inference Attacks](https://mlsanity.com/paper/2111.08440/) (2021)
- [Efficient Sharpness-aware Minimization for Improved Training of Neural Networks](https://mlsanity.com/paper/2110.03141/) (2021)
- [The Privacy Onion Effect: Memorization is Relative](https://mlsanity.com/paper/2206.10469/) (2022)
- [BYOL works even without batch statistics](https://mlsanity.com/paper/2010.10241/) (2020)
- [Toward Training at ImageNet Scale with Differential Privacy](https://mlsanity.com/paper/2201.12328/) (2022)
- [On the Privacy Risks of Algorithmic Fairness](https://mlsanity.com/paper/2011.03731/) (2020)
- [Robin Hood and Matthew Effects: Differential Privacy Has Disparate Impact on Synthetic Data](https://mlsanity.com/paper/2109.11429/) (2021)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?](https://mlsanity.com/paper/2106.12576/) (2021)
- [Not all noise is accounted equally: How differentially private learning benefits from large sampling rates](https://mlsanity.com/paper/2110.06255/) (2021)
- [A Blessing of Dimensionality in Membership Inference through Regularization](https://mlsanity.com/paper/2205.14055/) (2022)

## Built on by (most cited first, 1 of 1)

- [Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated Learning](https://mlsanity.com/paper/2609.03851/) (2026)

## Abstract (arXiv)

This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility. One focus of this work is sharpness-aware training (SAT) and its integration with differential privacy (DP-SAT) to further improve this balance. Additionally, we examine fairness in both private and non-private learning models trained on datasets with synthetic and real-world biases. We also measure the privacy risks involved in these scenarios by performing membership inference attacks (MIAs) and explore the consequences of eliminating high-privacy risk samples, termed outliers. Moreover, we introduce a new metric, named harmonic score, which combines accuracy, privacy, and fairness into a single measure. Through empirical analysis using generalization techniques, we achieve an accuracy of 81.11% under (8, 10-5)-DP on CIFAR-10, surpassing the 79.5% reported by De et al. (2022). Moreover, our experiments show that memorization of training samples can begin before the overfitting point, and generalization techniques do not guarantee the prevention of this memorization. Our analysis of synthetic biases shows that generalization techniques can amplify model bias in both private and non-private models. Additionally, our results indicate that increased bias in training data leads to reduced accuracy, greater vulnerability to privacy attacks, and higher model bias. We validate these findings with the CelebA dataset, demonstrating that similar trends persist with real-world attribute imbalances. Finally, our experiments show that removing outlier data decreases accuracy and further amplifies model bias.