Obálka

High-Speed Convolution Core Architecture for Privacy-Preserving Neural Networks

Uloženo v:
Vydáno v:Programming and Computer Software vol. 50, no. 6 (Dec 2024), p. 417
Hlavní autor: Lapina, M. A.
Další autoři: Shiriaev, E. M., Babenko, M. G., Istamov, I.
Vydáno:
Springer Nature B.V.
Témata:
Encryption
Big Data
Neurons
Personal information
Neural networks
Security
Artificial intelligence
Convolution
Privacy
Algorithms
Data encryption
Complexity
Cloud computing
Efficiency
On-line přístup:Citation/Abstract
Full Text
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstrakt:Due to legal restrictions or restrictions related to companies' internal information policies, businesses often do not trust sensitive information to public cloud providers. One of the mechanisms to ensure the security of sensitive data in clouds is homomorphic encryption. Privacy-preserving neural networks are used to design solutions that utilize neural networks under these conditions. They exploit the homomorphic encryption mechanism, thus enabling the security of commercial information in the cloud. The main deterrent to the use of privacy-preserving neural networks is the large computational and spatial complexity of the scalar multiplication algorithm, which is the basic algorithm for computing mathematical convolution. In this paper, we propose a scalar multiplication algorithm that reduces the spatial complexity from quadratic to linear, and reduces the computation time of scalar multiplication by a factor of 1.38.
ISSN:0361-7688
1608-3261
DOI:10.1134/S0361768824700282
Zdroj:Advanced Technologies & Aerospace Database