# Secure Quantized Training for Deep Learning

arXiv: https://arxiv.org/abs/2107.00501 · HTML: https://mlsanity.com/paper/2107.00501/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 78 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Gazelle: A Low Latency Framework for Secure Neural Network Inference](https://mlsanity.com/paper/1801.05507/) (2018)
- [Training Deep Neural Networks with 8-bit Floating Point Numbers](https://mlsanity.com/paper/1812.08011/) (2018)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [A generic framework for privacy preserving deep learning](https://mlsanity.com/paper/1811.04017/) (2018)
- [CrypTFlow2: Practical 2-Party Secure Inference](https://mlsanity.com/paper/2010.06457/) (2020)
- [Training Quantized Nets: A Deeper Understanding](https://mlsanity.com/paper/1706.02379/) (2017)
- [FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning](https://mlsanity.com/paper/2004.02229/) (2020)
- [Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications](https://mlsanity.com/paper/1801.03239/) (2018)
- [CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU](https://mlsanity.com/paper/2104.10949/) (2021)
- [QUOTIENT: Two-Party Secure Neural Network Training and Prediction](https://mlsanity.com/paper/1907.03372/) (2019)
- [Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data](https://mlsanity.com/paper/1911.07101/) (2019)
- [Secure Evaluation of Quantized Neural Networks](https://mlsanity.com/paper/1910.12435/) (2019)
- [Private Machine Learning in TensorFlow using Secure Computation](https://mlsanity.com/paper/1810.08130/) (2018)
- [secureTF: A Secure TensorFlow Framework](https://mlsanity.com/paper/2101.08204/) (2021)
- [Effectiveness of MPC-friendly Softmax Replacement](https://mlsanity.com/paper/2011.11202/) (2020)

## Built on by (most cited first, 15 of 15)

- [Secure Multiparty Computation for Synthetic Data Generation from Distributed Data](https://mlsanity.com/paper/2210.07332/) (2022)
- [Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects](https://mlsanity.com/paper/2304.08275/) (2023)
- [Attesting Distributional Properties of Training Data for Machine Learning](https://mlsanity.com/paper/2308.09552/) (2023)
- [UTrace: Poisoning Forensics for Private Collaborative Learning](https://mlsanity.com/paper/2409.15126/) (2024)
- [CryptoTrain: Fast Secure Training on Encrypted Dataset](https://mlsanity.com/paper/2409.16675/) (2024)
- [Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference](https://mlsanity.com/paper/2203.02833/) (2022)
- [WW-FL: Secure and Private Large-Scale Federated Learning](https://mlsanity.com/paper/2302.09904/) (2023)
- [CECILIA: Comprehensive Secure Machine Learning Framework](https://mlsanity.com/paper/2202.03023/) (2022)
- [Covert Attacks on Machine Learning Training in Passively Secure MPC](https://mlsanity.com/paper/2505.17092/) (2025)
- [DictPFL: Efficient and Private Federated Learning on Encrypted Gradients](https://mlsanity.com/paper/2510.21086/) (2025)
- [Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption](https://mlsanity.com/paper/2310.02563/) (2023)
- [Spin: An Efficient Secure Computation Framework with GPU Acceleration](https://mlsanity.com/paper/2402.02320/) (2024)
- [End to End Collaborative Synthetic Data Generation](https://mlsanity.com/paper/2412.03766/) (2024)
- [SLVR: Securely Leveraging Client Validation for Robust Federated Learning](https://mlsanity.com/paper/2502.08055/) (2025)
- [Secure and Privacy-Preserving Vertical Federated Learning](https://mlsanity.com/paper/2604.13474/) (2026)

## Abstract (arXiv)

We implement training of neural networks in secure multi-party computation (MPC) using quantization commonly used in said setting. We are the first to present an MNIST classifier purely trained in MPC that comes within 0.2 percent of the accuracy of the same convolutional neural network trained via plaintext computation. More concretely, we have trained a network with two convolutional and two dense layers to 99.2% accuracy in 3.5 hours (under one hour for 99% accuracy). We have also implemented AlexNet for CIFAR-10, which converges in a few hours. We develop novel protocols for exponentiation and inverse square root. Finally, we present experiments in a range of MPC security models for up to ten parties, both with honest and dishonest majority as well as semi-honest and malicious security.