Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network DesignDownload PDF

Published: 04 Nov 2021, Last Modified: 12 Mar 2024PRIML 2021 PosterReaders: Everyone
Keywords: neural networks, neural network architecture, differential privacy, privacy-preserving machine learning
TL;DR: We explore the relationship between neural network architectures and model accuracy under differential privacy constraints.
Abstract: We explore the relationship between neural network architectures and model accuracy under differential privacy constraints. Our findings show that architectures that perform well without differential privacy, do not necessarily do so with differential privacy. This shows that extant knowledge on neural network architecture design cannot be seamlessly translated into the differential privacy context. Moreover, as neural architecture search consumes privacy budget, future research is required to better understand the relationship between neural network architectures and model accuracy to enable better architecture design choices under differential privacy constraints.
Paper Under Submission: The paper is NOT under submission at NeurIPS
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2111.14924/code)
1 Reply

Loading