Operating system and method of a fully homomorphic encryption neural network model
Liu, Tzu-Li Ku, Yu-Te Ho, Ming-Chien Hsu, Chih-Fan Chen, Wei-Chao Liu, Feng-Hao Chang, Ming-Ching Hung, Shih-Hao
Liu, Tzu-Li
Ku, Yu-Te
Ho, Ming-Chien
Hsu, Chih-Fan
Chen, Wei-Chao
Liu, Feng-Hao
Chang, Ming-Ching
Hung, Shih-Hao
Supervisor
Department
Computer Science
Embargo End Date
Type
Patent
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
An operating method of a fully homomorphic encrypted neural network model is provided, wherein the fully homomorphic encrypted neural network model includes a plurality of layers, and the method performed by a processor includes: for one of the plurality of layers, encrypting a plaintext input with a first encryption algorithm to generate a ciphertext vector, performing a convolution operation according to the ciphertext vector to generate a result vector, transforming the result vector into a plurality of result ciphertexts adopting a second encryption algorithm, inputting the plurality of result ciphertexts into an activation function to generate a plurality of encrypted activation values, and repacking the plurality of encrypted activation values to generate an output vector adopting the first encryption algorithm.
Citation
“U.S. Patent Application for OPERATING SYSTEM AND METHOD OF A FULLY HOMOMORPHIC ENCRYPTION NEURAL NETWORK MODEL Patent Application (Application #20250086437 issued March 13, 2025) - Justia Patents Search.” Accessed: Apr. 15, 2025. [Online]. Available: https://patents.justia.com/patent/20250086437
Source
US Patent App. 18/545,775, 2025
Conference
Keywords
Subjects
Source
Publisher
Justia