Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference). (arXiv:2201.12577v2 [cs.CR] UPDATED)

In this work, we present a novel matrix-encoding method that is particularly
convenient for neural networks to make predictions in a privacy-preserving
manner using homomorphic encryption. Based on this encoding method, we
implement a convolutional neural network for handwritten image classification
over encryption. For two matrices $A$ and $B$ to perform homomorphic
multiplication, the main idea behind it, in a simple version, is to encrypt
matrix $A$ and the transpose of matrix $B$ into two ciphertexts respectively.
With additional operations, …

arxiv encoding inference networks neural networks privacy