# Crypto-Nets: Neural Networks over Encrypted Data

arXiv: https://arxiv.org/abs/1412.6181 · HTML: https://mlsanity.com/paper/1412.6181/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2014.

## Built on by (most cited first, 10 of 10)

- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [Security and Privacy for Artificial Intelligence: Opportunities and Challenges](https://mlsanity.com/paper/2102.04661/) (2021)
- [Demystifying Swarm Learning: A New Paradigm of Blockchain-based Decentralized Federated Learning](https://mlsanity.com/paper/2201.05286/) (2022)
- [Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits](https://mlsanity.com/paper/2302.06361/) (2023)
- [PolyDNN: Polynomial Representation of NN for Communication-less SMPC Inference](https://mlsanity.com/paper/2104.00863/) (2021)
- [MixNN: A design for protecting deep learning models](https://mlsanity.com/paper/2203.14803/) (2022)
- [Privacy-Preserving Wavelet Neural Network with Fully Homomorphic Encryption](https://mlsanity.com/paper/2205.13265/) (2022)
- [Privacy-Preserving Chaotic Extreme Learning Machine with Fully Homomorphic Encryption](https://mlsanity.com/paper/2208.02587/) (2022)
- [A Comparative Study of Image Disguising Methods for Confidential Outsourced Learning](https://mlsanity.com/paper/2301.00252/) (2022)
- [Homomorphic Encryptions for Privacy Preserving Vision](https://mlsanity.com/paper/2606.25216/) (2026)

## Abstract (arXiv)

The problem we address is the following: how can a user employ a predictive model that is held by a third party, without compromising private information. For example, a hospital may wish to use a cloud service to predict the readmission risk of a patient. However, due to regulations, the patient's medical files cannot be revealed. The goal is to make an inference using the model, without jeopardizing the accuracy of the prediction or the privacy of the data. To achieve high accuracy, we use neural networks, which have been shown to outperform other learning models for many tasks. To achieve the privacy requirements, we use homomorphic encryption in the following protocol: the data owner encrypts the data and sends the ciphertexts to the third party to obtain a prediction from a trained model. The model operates on these ciphertexts and sends back the encrypted prediction. In this protocol, not only the data remains private, even the values predicted are available only to the data owner. Using homomorphic encryption and modifications to the activation functions and training algorithms of neural networks, we show that it is protocol is possible and may be feasible. This method paves the way to build a secure cloud-based neural network prediction services without invading users' privacy.