TY - JOUR
T1 - T-BMPNet
T2 - Trainable Bitwise Multilayer Perceptron Neural Network over Fully Homomorphic Encryption Scheme
AU - Yoo, Joon Soo
AU - Yoon, Ji Won
N1 - Publisher Copyright:
© 2021 Joon Soo Yoo and Ji Won Yoon.
PY - 2021
Y1 - 2021
N2 - Homomorphic encryption (HE) is notable for enabling computation on encrypted data as well as guaranteeing high-level security based on the hardness of the lattice problem. In this sense, the advantage of HE has facilitated research that can perform data analysis in an encrypted state as a purpose of achieving security and privacy for both clients and the cloud. However, much of the literature is centered around building a network that only provides an encrypted prediction result rather than constructing a system that can learn from the encrypted data to provide more accurate answers for the clients. Moreover, their research uses simple polynomial approximations to design an activation function causing a possibly significant error in prediction results. Conversely, our approach is more fundamental; we present t-BMPNet which is a neural network over fully homomorphic encryption scheme that is built upon primitive gates and fundamental bitwise homomorphic operations. Thus, our model can tackle the nonlinearity problem of approximating the activation function in a more sophisticated way. Moreover, we show that our t-BMPNet can perform training - backpropagation and feedforward algorithms - in the encrypted domain, unlike other literature. Last, we apply our approach to a small dataset to demonstrate the feasibility of our model.
AB - Homomorphic encryption (HE) is notable for enabling computation on encrypted data as well as guaranteeing high-level security based on the hardness of the lattice problem. In this sense, the advantage of HE has facilitated research that can perform data analysis in an encrypted state as a purpose of achieving security and privacy for both clients and the cloud. However, much of the literature is centered around building a network that only provides an encrypted prediction result rather than constructing a system that can learn from the encrypted data to provide more accurate answers for the clients. Moreover, their research uses simple polynomial approximations to design an activation function causing a possibly significant error in prediction results. Conversely, our approach is more fundamental; we present t-BMPNet which is a neural network over fully homomorphic encryption scheme that is built upon primitive gates and fundamental bitwise homomorphic operations. Thus, our model can tackle the nonlinearity problem of approximating the activation function in a more sophisticated way. Moreover, we show that our t-BMPNet can perform training - backpropagation and feedforward algorithms - in the encrypted domain, unlike other literature. Last, we apply our approach to a small dataset to demonstrate the feasibility of our model.
UR - http://www.scopus.com/inward/record.url?scp=85121652548&partnerID=8YFLogxK
U2 - 10.1155/2021/7621260
DO - 10.1155/2021/7621260
M3 - Article
AN - SCOPUS:85121652548
SN - 1939-0122
VL - 2021
JO - Security and Communication Networks
JF - Security and Communication Networks
M1 - 7621260
ER -