A Simple Solution for Homomorphic Evaluation on Large Intervals

J Chiang - arXiv preprint arXiv:2405.15201, 2024 - arxiv.org
Homomorphic encryption (HE) is a promising technique used for privacy-preserving
computation. Since HE schemes only support primitive polynomial operations, homomorphic …

Privacy-Preserving 3-Layer Neural Network Training using Mere Homomorphic Encryption Technique

J Chiang - arXiv preprint arXiv:2308.09531, 2023 - arxiv.org
In this manuscript, we consider the problem of privacy-preserving training of neural networks
in the mere homomorphic encryption setting. We combine several exsiting techniques …

LFFR: Logistic Function For (single-output) Regression

J Chiang - arXiv preprint arXiv:2407.09955, 2024 - arxiv.org
Privacy-preserving regression in machine learning is a crucial area of research, aimed at
enabling the use of powerful machine learning techniques while protecting individuals' …