# NN-EMD: Efficiently Training Neural Networks using Encrypted Multi-Sourced Datasets

arXiv: https://arxiv.org/abs/2012.10547 · HTML: https://mlsanity.com/paper/2012.10547/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Privacy-Preserving Machine Learning: Methods, Challenges and Directions](https://mlsanity.com/paper/2108.04417/) (2021)
- [Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation](https://mlsanity.com/paper/2504.19101/) (2025)
- [TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2501.05053/) (2025)
- [Evaluating Scenario-based Decision-making for Interactive Autonomous Driving Using Rational Criteria: A Survey](https://mlsanity.com/paper/2501.01886/) (2025)
- [Edge Deep Learning Model Protection via Neuron Authorization](https://mlsanity.com/paper/2303.12397/) (2023)
- [Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption](https://mlsanity.com/paper/2310.02563/) (2023)

## Abstract (arXiv)

Training a machine learning model over an encrypted dataset is an existing promising approach to address the privacy-preserving machine learning task, however, it is extremely challenging to efficiently train a deep neural network (DNN) model over encrypted data for two reasons: first, it requires large-scale computation over huge datasets; second, the existing solutions for computation over encrypted data, such as homomorphic encryption, is inefficient. Further, for an enhanced performance of a DNN model, we also need to use huge training datasets composed of data from multiple data sources that may not have pre-established trust relationships among each other. We propose a novel framework, NN-EMD, to train DNN over multiple encrypted datasets collected from multiple sources. Toward this, we propose a set of secure computation protocols using hybrid functional encryption schemes. We evaluate our framework for performance with regards to the training time and model accuracy on the MNIST datasets. Compared to other existing frameworks, our proposed NN-EMD framework can significantly reduce the training time, while providing comparable model accuracy and privacy guarantees as well as supporting multiple data sources. Furthermore, the depth and complexity of neural networks do not affect the training time despite introducing a privacy-preserving NN-EMD setting.