We present an approach to outsourcing of training neural networks while preserving data confidentiality from malicious parties. We use fully homomorphic encryption to build a unified training approach that works on encrypted data and learns quantized neural network models. The data can be horizontally or vertically split between multiple parties, enabling collaboration on confidential data. We train logistic regression and multi-layer perceptrons on several datasets.
@article{arxiv.2401.16136,
title = {Neural Network Training on Encrypted Data with TFHE},
author = {Luis Montero and Jordan Frery and Celia Kherfallah and Roman Bredehoft and Andrei Stoian},
journal= {arXiv preprint arXiv:2401.16136},
year = {2024}
}