# Training Differentially Private Models with Secure Multiparty Computation

arXiv: https://arxiv.org/abs/2202.02625 · HTML: https://mlsanity.com/paper/2202.02625/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 59 references that are in the map.
- First posted on arXiv 5 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [Machine Learning Models that Remember Too Much](https://mlsanity.com/paper/1709.07886/) (2017)
- [Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications](https://mlsanity.com/paper/2010.05867/) (2020)
- [Protecting Privacy of Users in Brain-Computer Interface Applications](https://mlsanity.com/paper/1907.01586/) (2019)
- [Privacy-Preserving Feature Selection with Secure Multiparty Computation](https://mlsanity.com/paper/2102.03517/) (2021)
- [High Performance Logistic Regression for Privacy-Preserving Genome Analysis](https://mlsanity.com/paper/2002.05377/) (2020)
- [Secure multiparty computations in floating-point arithmetic](https://mlsanity.com/paper/2001.03192/) (2020)
- [Privacy-Preserving Training of Tree Ensembles over Continuous Data](https://mlsanity.com/paper/2106.02769/) (2021)
- [PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy](https://mlsanity.com/paper/2110.11578/) (2021)
- [Comparison among dimensionality reduction techniques based on Random Projection for cancer classification](https://mlsanity.com/paper/1608.07019/) (2016)
- [Achieving Secure and Differentially Private Computations in Multiparty Settings](https://mlsanity.com/paper/1707.01871/) (2017)

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

- [Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications](https://mlsanity.com/paper/2506.00660/) (2025)
- [SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy](https://mlsanity.com/paper/2601.09460/) (2026)

## Abstract (arXiv)

We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on Differential Privacy (DP) achieve this at the cost of a drop in accuracy. Solutions based on Secure Multiparty Computation (MPC) do not incur such accuracy loss but leak information when the trained model is made publicly available. We propose an MPC solution for training DP models. Our solution relies on an MPC protocol for model training, and an MPC protocol for perturbing the trained model coefficients with Laplace noise in a privacy-preserving manner. The resulting MPC+DP approach achieves higher accuracy than a pure DP approach while providing the same formal privacy guarantees. Our work obtained first place in the iDASH2021 Track III competition on confidential computing for secure genome analysis.