# QUOTIENT: Two-Party Secure Neural Network Training and Prediction

arXiv: https://arxiv.org/abs/1907.03372 · HTML: https://mlsanity.com/paper/1907.03372/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2019.

## Built on by (most cited first, 30 of 41)

- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [Label Leakage and Protection in Two-party Split Learning](https://mlsanity.com/paper/2102.08504/) (2021)
- [Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage](https://mlsanity.com/paper/2203.15696/) (2022)
- [Privacy-Preserving Machine Learning: Methods, Challenges and Directions](https://mlsanity.com/paper/2108.04417/) (2021)
- [SIRNN: A Math Library for Secure RNN Inference](https://mlsanity.com/paper/2105.04236/) (2021)
- [A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacy](https://mlsanity.com/paper/2302.10637/) (2023)
- [Defending against Reconstruction Attack in Vertical Federated Learning](https://mlsanity.com/paper/2107.09898/) (2021)
- [Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs](https://mlsanity.com/paper/2105.12049/) (2021)
- [Secure Quantized Training for Deep Learning](https://mlsanity.com/paper/2107.00501/) (2021)
- [AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference](https://mlsanity.com/paper/2201.06699/) (2022)
- [Privacy-Preserving Feature Selection with Secure Multiparty Computation](https://mlsanity.com/paper/2102.03517/) (2021)
- [Privacy-Preserving Video Classification with Convolutional Neural Networks](https://mlsanity.com/paper/2102.03513/) (2021)
- [Ditto: Quantization-aware Secure Inference of Transformers upon MPC](https://mlsanity.com/paper/2405.05525/) (2024)
- [Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learning](https://mlsanity.com/paper/2404.09265/) (2024)
- [Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey](https://mlsanity.com/paper/2105.06300/) (2021)
- [Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimation](https://mlsanity.com/paper/2106.02203/) (2021)
- [PrivFair: a Library for Privacy-Preserving Fairness Auditing](https://mlsanity.com/paper/2202.04058/) (2022)
- [Federated Zero-Shot Learning for Visual Recognition](https://mlsanity.com/paper/2209.01994/) (2022)
- [PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacy](https://mlsanity.com/paper/2110.11578/) (2021)
- [Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives](https://mlsanity.com/paper/2406.10884/) (2024)
- [CryptoTrain: Fast Secure Training on Encrypted Dataset](https://mlsanity.com/paper/2409.16675/) (2024)
- [Fast Privacy-Preserving Text Classification based on Secure Multiparty Computation](https://mlsanity.com/paper/2101.07365/) (2021)
- [Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training](https://mlsanity.com/paper/2403.03592/) (2024)
- [MPC-Friendly Commitments for Publicly Verifiable Covert Security](https://mlsanity.com/paper/2109.07461/) (2021)
- [Towards Privacy-Preserving Neural Architecture Search](https://mlsanity.com/paper/2204.10958/) (2022)
- [SelectFormer: Private and Practical Data Selection for Transformers](https://mlsanity.com/paper/2310.02373/) (2023)
- [Edge AI for Internet of Energy: Challenges and Perspectives](https://mlsanity.com/paper/2311.16851/) (2023)
- [Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption](https://mlsanity.com/paper/2403.11166/) (2024)
- [Privacy-Preserving Hierarchical Model-Distributed Inference](https://mlsanity.com/paper/2407.18353/) (2024)

## Abstract (arXiv)

Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). However, as DNNs are trained on data, a key question is how such models can be also trained securely. The few prior works on secure DNN training have focused either on designing custom protocols for existing training algorithms, or on developing tailored training algorithms and then applying generic secure protocols. In this work, we investigate the advantages of designing training algorithms alongside a novel secure protocol, incorporating optimizations on both fronts. We present QUOTIENT, a new method for discretized training of DNNs, along with a customized secure two-party protocol for it. QUOTIENT incorporates key components of state-of-the-art DNN training such as layer normalization and adaptive gradient methods, and improves upon the state-of-the-art in DNN training in two-party computation. Compared to prior work, we obtain an improvement of 50X in WAN time and 6% in absolute accuracy.