mlsanityData to 7 Oct 2026

Secure Quantized Training for Deep Learning

arXiv 2107.00501 ↗First posted 1 Jul 2021cs.LGcited by 15

Not on the map. Why?

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 19 of its 78 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

19 of 78 references.

References · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2019On the Convergence of Adam and Beyondcited by 834
  5. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  6. 2018Training Deep Neural Networks with 8-bit Floating Point Numberscited by 163
  7. 2015Fixed Point Quantization of Deep Convolutional Networkscited by 141
  8. 2018A generic framework for privacy preserving deep learningcited by 103
  9. 2020CrypTFlow2: Practical 2-Party Secure Inferencecited by 82
  10. 2017Training Quantized Nets: A Deeper Understandingcited by 74
  11. 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
  12. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
7 more
  1. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  2. 2019QUOTIENT: Two-Party Secure Neural Network Training and Predictioncited by 41
  3. 2019Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Datacited by 28
  4. 2019Secure Evaluation of Quantized Neural Networkscited by 22
  5. 2018Private Machine Learning in TensorFlow using Secure Computationcited by 15
  6. 2021secureTF: A Secure TensorFlow Frameworkcited by 12
  7. 2020Effectiveness of MPC-friendly Softmax Replacementcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 4; 2024: 4; 2025: 3; 2026: 1.

15 papers.

Sort:

  1. 2022Secure Multiparty Computation for Synthetic Data Generation from Distributed Datacited by 6
  2. 2023Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspectscited by 5
  3. 2023Attesting Distributional Properties of Training Data for Machine Learningcited by 5
  4. 2024UTrace: Poisoning Forensics for Private Collaborative Learningcited by 3
  5. 2024CryptoTrain: Fast Secure Training on Encrypted Datasetcited by 3
  6. 2022Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inferencecited by 2
  7. 2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
  8. 2022CECILIA: Comprehensive Secure Machine Learning Frameworkcited by 1
  9. 2025Covert Attacks on Machine Learning Training in Passively Secure MPCcited by 1
  10. 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradientscited by 1
  11. 2023Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryptioncited by 0
  12. 2024Spin: An Efficient Secure Computation Framework with GPU Accelerationcited by 0
3 more
  1. 2024End to End Collaborative Synthetic Data Generationcited by 0
  2. 2025SLVR: Securely Leveraging Client Validation for Robust Federated Learningcited by 0
  3. 2026Secure and Privacy-Preserving Vertical Federated Learningcited by 0