Training neural network over encrypted data
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F20%3AA21025BN" target="_blank" >RIV/61988987:17610/20:A21025BN - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/abstract/document/9204073" target="_blank" >https://ieeexplore.ieee.org/abstract/document/9204073</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/DSMP47368.2020.9204073" target="_blank" >10.1109/DSMP47368.2020.9204073</a>
Alternative languages
Result language
angličtina
Original language name
Training neural network over encrypted data
Original language description
We are answering the question whenever systems with convolutional neural network classifier trained over plain and encrypted data keep the ordering according to accuracy. Our motivation is need for designing convolutional neural network classifiers when data in their plain form are not accessible because of private company policy or sensitive data gathered by police. We propose to use a combination of fully connected autoencoder together with a convolutional neural network classifier. The autoencoder transforms the data info form that allows the convolutional classifier to be trained. We present three experiments that show the ordering of systems over plain and encrypted data. The results show that the systems indeed keep the ordering, and thus a NN designer can select appropriate architecture over encrypted data and later let data owner train or fine-tune the system/CNN classifier on the plain data.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10102 - Applied mathematics
Result continuities
Project
<a href="/en/project/EF17_049%2F0008414" target="_blank" >EF17_049/0008414: Centre for the development of Artificial Intelligence Methods for the Automotive Industry of the region</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of IEEE Third International Conference Data Stream Mining & Processing 2020
ISBN
978-1-7281-3214-3
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
23-27
Publisher name
IEEE
Place of publication
—
Event location
Lviv, Ukrajina
Event date
Jan 1, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—