TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Image Classification	CIFAR-10	SmoothNetV1	Percentage correct	73.5	# 223
Image Classification	Imagenette	SmoothNetV1	Accuracy	69.7	# 2

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/smoothnets-optimizing-cnn-architecture-design/image-classification-on-imagenette)](https://paperswithcode.com/sota/image-classification-on-imagenette?p=smoothnets-optimizing-cnn-architecture-design)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/smoothnets-optimizing-cnn-architecture-design/image-classification-on-cifar-10)](https://paperswithcode.com/sota/image-classification-on-cifar-10?p=smoothnets-optimizing-cnn-architecture-design)`

SmoothNets: Optimizing CNN architecture design for differentially private deep learning

9 May 2022 · Nicolas W. Remerscheid, Alexander Ziller, Daniel Rueckert, Georgios Kaissis ·

The arguably most widely employed algorithm to train deep neural networks with Differential Privacy is DPSGD, which requires clipping and noising of per-sample gradients. This introduces a reduction in model utility compared to non-private training. Empirically, it can be observed that this accuracy degradation is strongly dependent on the model architecture. We investigated this phenomenon and, by combining components which exhibit good individual performance, distilled a new model architecture termed SmoothNet, which is characterised by increased robustness to the challenges of DP-SGD training. Experimentally, we benchmark SmoothNet against standard architectures on two benchmark datasets and observe that our architecture outperforms others, reaching an accuracy of 73.5\% on CIFAR-10 at $\varepsilon=7.0$ and 69.2\% at $\varepsilon=7.0$ on ImageNette, a state-of-the-art result compared to prior architectural modifications for DP.

PDF Abstract