# Privacy-Preserving 3-Layer Neural Network Training

arXiv: https://arxiv.org/abs/2308.09531 · HTML: https://mlsanity.com/paper/2308.09531/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Builds on (most cited first, 9 of 9)

- [Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference](https://mlsanity.com/paper/1811.09953/) (2018)
- [POSEIDON: Privacy-Preserving Federated Neural Network Learning](https://mlsanity.com/paper/2009.00349/) (2020)
- [Polynomial Regression As an Alternative to Neural Nets](https://mlsanity.com/paper/1806.06850/) (2018)
- [Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant](https://mlsanity.com/paper/2201.10838/) (2022)
- [Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)](https://mlsanity.com/paper/2201.12577/) (2022)
- [Multinomial Logistic Regression Algorithms via Quadratic Gradient](https://mlsanity.com/paper/2208.06828/) (2022)
- [On Polynomial Approximation of Activation Function](https://mlsanity.com/paper/2202.00004/) (2022)
- [Privacy-Preserving CNN Training with Transfer Learning: Multiclass Logistic Regression](https://mlsanity.com/paper/2304.03807/) (2023)
- [Activation Functions Not To Active: A Plausible Theory on Interpreting Neural Networks](https://mlsanity.com/paper/2305.00663/) (2023)

## Built on by (most cited first, 1 of 1)

- [LFFR: Logistic Function For (single-output) Regression](https://mlsanity.com/paper/2407.09955/) (2024)

## Abstract (arXiv)

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 available, extend some of them, and finally enable the training of 3-layer neural networks for both the regression and classification problems using mere homomorphic encryption technique.