# Exploring Machine Learning Privacy/Utility trade-off from a hyperparameters Lens

arXiv: https://arxiv.org/abs/2303.01819 · HTML: https://mlsanity.com/paper/2303.01819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 3 Mar 2023.

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

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [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)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Tempered Sigmoid Activations for Deep Learning with Differential Privacy](https://mlsanity.com/paper/2007.14191/) (2020)
- [Hyperparameter Tuning with Renyi Differential Privacy](https://mlsanity.com/paper/2110.03620/) (2021)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Model Stealing Attacks Against Inductive Graph Neural Networks](https://mlsanity.com/paper/2112.08331/) (2021)
- [On the Convergence and Calibration of Deep Learning with Differential Privacy](https://mlsanity.com/paper/2106.07830/) (2021)
- [Three Tools for Practical Differential Privacy](https://mlsanity.com/paper/1812.02890/) (2018)
- [Efficient Hyperparameter Optimization for Differentially Private Deep Learning](https://mlsanity.com/paper/2108.03888/) (2021)

## Abstract (arXiv)

Machine Learning (ML) architectures have been applied to several applications that involve sensitive data, where a guarantee of users' data privacy is required. Differentially Private Stochastic Gradient Descent (DPSGD) is the state-of-the-art method to train privacy-preserving models. However, DPSGD comes at a considerable accuracy loss leading to sub-optimal privacy/utility trade-offs. Towards investigating new ground for better privacy-utility trade-off, this work questions; (i) if models' hyperparameters have any inherent impact on ML models' privacy-preserving properties, and (ii) if models' hyperparameters have any impact on the privacy/utility trade-off of differentially private models. We propose a comprehensive design space exploration of different hyperparameters such as the choice of activation functions, the learning rate and the use of batch normalization. Interestingly, we found that utility can be improved by using Bounded RELU as activation functions with the same privacy-preserving characteristics. With a drop-in replacement of the activation function, we achieve new state-of-the-art accuracy on MNIST (96.02%), FashionMnist (84.76%), and CIFAR-10 (44.42%) without any modification of the learning procedure fundamentals of DPSGD.