Neural Network Quantisation for Faster Homomorphic Encryption

ePrint Report: Neural Network Quantisation for Faster Homomorphic Encryption

Wouter Legiest, Jan-Pieter D'Anvers, Michiel Van Beirendonck, Furkan Turan, Ingrid Verbauwhede

Homomorphic encryption (HE) enables calculating
on encrypted data, which makes it possible to perform privacy-
preserving neural network inference. One disadvantage of this
technique is that it is several orders of magnitudes slower than
calculation on unencrypted data. Neural networks are commonly
trained using floating-point, while most homomorphic encryption
libraries calculate on integers, thus requiring a quantisation of the
neural …

data encrypted encrypted data encryption eprint report homomorphic encryption integer large network networks neural network neural networks point privacy report unencrypted unencrypted data van