Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
A STUDY OF USING CKKS HOMOMORPHIC ENCRYPTION OVER THE LAYERS OF A CONVOLUTIONAL NEURAL NETWORK MODEL |
¿µ¹®Á¦¸ñ(English Title) |
A STUDY OF USING CKKS HOMOMORPHIC ENCRYPTION OVER THE LAYERS OF A CONVOLUTIONAL NEURAL NETWORK MODEL |
ÀúÀÚ(Author) |
Sebastian Soler Castaneda
Kevin Nam
Youyeon Joo
Yunheung Paek
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 29 NO. 01 PP. 0161 ~ 0164 (2022. 05) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
Homomorphic Encryption (HE) schemes have been recently growing as a reliable solution to preserve users¡¯ information owe to maintaining and operating the user data in the encrypted state. In addition to that, several Neural Networks models merged with HE schemes have been developed as a prospective tool for privacypreserving machine learning. Those mentioned works demonstrated that it is possible to match the accuracy of non-encrypted models but there is always a trade-off in the computation time. In this work, we evaluate the implementation of CKKS HE scheme operations over the layers of a LeNet5 convolutional inference model, however, owing to the limitations of the evaluation environment, the scope of this work is not to develop a complete LeNet5 encrypted model. The evaluation was performed using the MNIST dataset with Microsoft SEAL(MSEAL) open-source homomorphic encryption library ported version on Python (PyFhel). The behavior of the encrypted model, the limitations faced and a small description of related and future work is also provided. |
Å°¿öµå(Keyword) |
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|