English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the era of big data, deep learning has become an increasingly populartopic. It has outstanding achievements in the fields of image recognition,object detection, and natural language processing et al. The first priority ofdeep learning is exploiting valuable information from a large amount of data,which will inevitably induce privacy issues that are worthy of attention.Presently, several privacy-preserving deep learning methods have been proposed,but most of them suffer from a non-negligible degradation of either efficiencyor accuracy. Negative database (\textit{NDB}) is a new type of datarepresentation which can protect data privacy by storing and utilizing thecomplementary form of original data. In this paper, we propose aprivacy-preserving deep learning method named NegDL based on \textit{NDB}.Specifically, private data are first converted to \textit{NDB} as the input ofdeep learning models by a generation algorithm called \textit{QK}-hiddenalgorithm, and then the sketches of \textit{NDB} are extracted for training andinference. We demonstrate that the computational complexity of NegDL is thesame as the original deep learning model without privacy protection.Experimental results on Breast Cancer, MNIST, and CIFAR-10 benchmark datasetsdemonstrate that the accuracy of NegDL could be comparable to the original deeplearning model in most cases, and it performs better than the method based ondifferential privacy.

NegDL: Privacy-Preserving Deep Learning Based on Negative Database