# Impact of Privacy Parameters on Deep Learning Models for Image Classification

arXiv: https://arxiv.org/abs/2412.06689 · HTML: https://mlsanity.com/paper/2412.06689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 9 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://mlsanity.com/paper/1711.00489/) (2017)
- [Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy](https://mlsanity.com/paper/2205.10683/) (2022)
- [Bounding Training Data Reconstruction in Private (Deep) Learning](https://mlsanity.com/paper/2201.12383/) (2022)
- [Selective Network Linearization for Efficient Private Inference](https://mlsanity.com/paper/2202.02340/) (2022)
- [Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning](https://mlsanity.com/paper/2209.07716/) (2022)
- [Transfer Learning In Differential Privacy's Hybrid-Model](https://mlsanity.com/paper/2201.12018/) (2022)
- [Privacy-Preserving Image Classification in the Local Setting](https://mlsanity.com/paper/2002.03261/) (2020)

## Abstract (arXiv)

The project aims to develop differentially private deep learning models for image classification on CIFAR-10 datasets citecifar10 and analyze the impact of various privacy parameters on model accuracy. We have implemented five different deep learning models, namely ConvNet, ResNet18, EfficientNet, ViT, and DenseNet121 and three supervised classifiers namely K-Nearest Neighbors, Naive Bayes Classifier and Support Vector Machine. We evaluated the performance of these models under varying settings. Our best performing model to date is EfficientNet with test accuracy of 59.63% with the following parameters (Adam optimizer, batch size 256, epoch size 100, epsilon value 5.0, learning rate 1e-3, clipping threshold 1.0, and noise multiplier 0.912).