SecureBP from Homomorphic Encryption
Joint Authors
Zhou, Shuai
Liu, Qinju
Lu, Xianhui
Luo, Fucai
He, Jingnan
Wang, Kunpeng
Source
Security and Communication Networks
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-06-12
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Information Technology and Computer Science
Abstract EN
We present a secure backpropagation neural network training model (SecureBP), which allows a neural network to be trained while retaining the confidentiality of the training data, based on the homomorphic encryption scheme.
We make two contributions.
The first one is to introduce a method to find a more accurate and numerically stable polynomial approximation of functions in a certain interval.
The second one is to find a strategy of refreshing ciphertext during training, which keeps the order of magnitude of noise at O˜e33.
American Psychological Association (APA)
Liu, Qinju& Lu, Xianhui& Luo, Fucai& Zhou, Shuai& He, Jingnan& Wang, Kunpeng. 2020. SecureBP from Homomorphic Encryption. Security and Communication Networks،Vol. 2020, no. 2020, pp.1-9.
https://search.emarefa.net/detail/BIM-1208444
Modern Language Association (MLA)
Liu, Qinju…[et al.]. SecureBP from Homomorphic Encryption. Security and Communication Networks No. 2020 (2020), pp.1-9.
https://search.emarefa.net/detail/BIM-1208444
American Medical Association (AMA)
Liu, Qinju& Lu, Xianhui& Luo, Fucai& Zhou, Shuai& He, Jingnan& Wang, Kunpeng. SecureBP from Homomorphic Encryption. Security and Communication Networks. 2020. Vol. 2020, no. 2020, pp.1-9.
https://search.emarefa.net/detail/BIM-1208444
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1208444