no code implementations • 18 Aug 2023 • John Chiang
In this manuscript, we consider the problem of privacy-preserving training of neural networks in the mere homomorphic encryption setting.
no code implementations • 1 May 2023 • John Chiang
This $\textit{ Super Space }$ is something like a coordinate system, in which every multivalue function can be represented by a $\textit{ Super Plane }$.
no code implementations • 7 Apr 2023 • John Chiang
; and (4) we use a simple but flexible matrix-encoding method named $\texttt{Volley Revolver}$ to manage the data flow in the ciphertexts, which is the key factor to complete the whole homomorphic CNN training.
no code implementations • 3 Sep 2022 • John Chiang
Also, Chiang speculates that there might be a relation between the Hessian matrix and the learning rate for the first-order gradient descent method.
no code implementations • 14 Aug 2022 • John Chiang
A recently work proposed a faster gradient called $\texttt{quadratic gradient}$ that can accelerate the binary logistic regression training, and presented an enhanced Nesterov's accelerated gradient (NAG) method for binary logistic regression.
1 code implementation • 29 Jan 2022 • John Chiang
In a public cloud with 40 vCPUs, our convolutional neural network implementation on the MNIST testing dataset takes $\sim$ 287 seconds to compute ten likelihoods of 32 encrypted images of size $28 \times 28$ simultaneously.
1 code implementation • 29 Jan 2022 • John Chiang
In this work, we propose an interesting method that aims to approximate an activation function over some domain by polynomials of the presupposing low degree.
1 code implementation • 26 Jan 2022 • John Chiang
In this paper, we propose a faster gradient variant called $\texttt{quadratic gradient}$ for privacy-preserving logistic regression training.