Content area

Abstract

The growth of cloud computing has encouraged resource-constrained data owners to upload skeleton data to the cloud for action identification, but this practice increases the risk of privacy breaches. Although the traditional anonymized privacy protection method protects the user privacy, it sacrifices the performance of action recognition. To solve the above problems, a Convolutional Neural Network (CNN) architecture compatible with Fully Homomorphic Encryption (FHE) is proposed in this paper, which can achieve secure action recognition without sacrificing the accuracy of action recognition. In addition, to solve the problem of low computational efficiency of the Residue Number System (RNS) variant of CKKS (RNS-CKKS) applied to CNN networks, a parallel fully homomorphic convolution method is designed to improve computational efficiency. To reduce the overhead of rotating key generation and transmission, a multi-layer key generation system is constructed. Finally, the superiority of the proposed model is verified on real data sets.

Details

Title
Cloud-based secure human action recognition with fully homomorphic encryption
Author
Wang, Ruyan 1 ; Zeng, Qinglin 1 ; Yang, Zhigang 2 ; Zhang, Puning 1 

 Chongqing University of Posts and Telecommunications, School of Communications and Information Engineering, Chongqing, China (GRID:grid.411587.e) (ISNI:0000 0001 0381 4112); The Advanced Network and Intelligent Connection Technology Key Laboratory, Chongqing, China (GRID:grid.411587.e); Key Laboratory of Ubiquitous Sensing and Networking, Chongqing, China (GRID:grid.411587.e) 
 Chongqing University of Posts and Telecommunications, School of Cyber Security and Information Law, Chongqing, China (GRID:grid.411587.e) (ISNI:0000 0001 0381 4112); The Advanced Network and Intelligent Connection Technology Key Laboratory, Chongqing, China (GRID:grid.411587.e); Key Laboratory of Ubiquitous Sensing and Networking, Chongqing, China (GRID:grid.411587.e) 
Publication title
Volume
81
Issue
1
Pages
12
Publication year
2025
Publication date
Jan 2025
Publisher
Springer Nature B.V.
Place of publication
New York
Country of publication
Netherlands
Publication subject
ISSN
09208542
e-ISSN
15730484
Source type
Scholarly Journal
Language of publication
English
Document type
Journal Article
Publication history
 
 
Online publication date
2024-10-16
Milestone dates
2024-10-07 (Registration); 2024-09-26 (Accepted)
Publication history
 
 
   First posting date
16 Oct 2024
ProQuest document ID
3256610761
Document URL
https://www.proquest.com/scholarly-journals/cloud-based-secure-human-action-recognition-with/docview/3256610761/se-2?accountid=208611
Copyright
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
Last updated
2025-10-03
Database
ProQuest One Academic