다양한 차수의 합성 미니맥스 근사 다항식이 완전 동형 암호 상에서의 컨볼루션 신경망 네트워크에 미치는 영향
Vol. 33, No. 6, pp. 861-868,
12월.
2023
JKIISC.2023.33.6.861, Full Text:
Keywords: Fully homomorphic encryption, Privacy-Preserving Machine Learning, Composite Minimax Polynomial, Convolutional Neural Network
Abstract Statistics
Cite this article
JKIISC.2023.33.6.861, Full Text:
Keywords: Fully homomorphic encryption, Privacy-Preserving Machine Learning, Composite Minimax Polynomial, Convolutional Neural Network
Abstract Statistics
Cite this article
[IEEE Style]
이정현 and 노종선, "The Impact of Various Degrees of Composite Minimax Approximate Polynomials on Convolutional Neural Networks over Fully Homomorphic Encryption," Journal of The Korea Institute of Information Security and Cryptology, vol. 33, no. 6, pp. 861-868, 2023. DOI: JKIISC.2023.33.6.861.
[ACM Style]
이정현 and 노종선. 2023. The Impact of Various Degrees of Composite Minimax Approximate Polynomials on Convolutional Neural Networks over Fully Homomorphic Encryption. Journal of The Korea Institute of Information Security and Cryptology, 33, 6, (2023), 861-868. DOI: JKIISC.2023.33.6.861.