Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition

DOI10.1016/j.neunet.2020.02.001zbMath1434.68507DBLPjournals/nn/GongPXQT20OpenAlexW3006463092WikidataQ89845125 ScholiaQ89845125MaRDI QIDQ2185767

A. K. Qin, Yu Xie, Maoguo Gong, Ke Pan, Zedong Tang

Publication date: 5 June 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2020.02.001

zbMATH Keywords

differential privacydeep neural networksrelevance analysis

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Privacy of data (68P27)

Uses Software

• UCI-ml
• darch
• ImageNet
• Adam
• AlexNet

Cites Work

• Unnamed Item
• Auto-association by multilayer perceptrons and singular value decomposition
• Preserving differential privacy in convolutional deep belief networks
• Towards easier and faster sequence labeling for natural language processing: a search-based probabilistic online learning framework (SAPO)
• Flexible unsupervised feature extraction for image classification
• The Algorithmic Foundations of Differential Privacy
• A Fast Learning Algorithm for Deep Belief Nets
• Some methods of speeding up the convergence of iteration methods
• Theory of Cryptography

This page was built for publication: Preserving differential privacy in deep neural networks with relevance-based adaptive noise imposition