# Neural Network Training on Encrypted Data with TFHE

arXiv: https://arxiv.org/abs/2401.16136 · HTML: https://mlsanity.com/paper/2401.16136/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 12 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 3 of 3)

- [Training and Inference with Integers in Deep Neural Networks](https://mlsanity.com/paper/1802.04680/) (2018)
- [Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data](https://mlsanity.com/paper/1911.07101/) (2019)
- [NITI: Training Integer Neural Networks Using Integer-only Arithmetic](https://mlsanity.com/paper/2009.13108/) (2020)

## Built on by (most cited first, 2 of 2)

- [ReBoot: Encrypted Training of Deep Neural Networks with CKKS Bootstrapping](https://mlsanity.com/paper/2506.19693/) (2025)
- [An End-to-End Homomorphically Encrypted Neural Network](https://mlsanity.com/paper/2502.16176/) (2025)

## Abstract (arXiv)

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.