mlsanityData to 7 Oct 2026

QUOTIENT: Two-Party Secure Neural Network Training and Prediction

arXiv 1907.03372 ↗First posted 8 Jul 2019cs.CR cs.LGcited by 41

Not on the map. Why?

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.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 6; 2023: 3; 2024: 11; 2025: 3; 2026: 1.

41 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2021Trustworthy AI: A Computational Perspectivecited by 93
  3. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  4. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  5. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  6. 2021SIRNN: A Math Library for Secure RNN Inferencecited by 28
  7. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  8. 2021Defending against Reconstruction Attack in Vertical Federated Learningcited by 20
  9. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  10. 2021Secure Quantized Training for Deep Learningcited by 15
  11. 2022AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inferencecited by 14
  12. 2021Privacy-Preserving Feature Selection with Secure Multiparty Computationcited by 12
29 more
  1. 2021Privacy-Preserving Video Classification with Convolutional Neural Networkscited by 10
  2. 2024Ditto: Quantization-aware Secure Inference of Transformers upon MPCcited by 7
  3. 2024Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learningcited by 6
  4. 2021Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Surveycited by 4
  5. 2021Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimationcited by 4
  6. 2022PrivFair: a Library for Privacy-Preserving Fairness Auditingcited by 4
  7. 2022Federated Zero-Shot Learning for Visual Recognitioncited by 4
  8. 2021PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacycited by 3
  9. 2024Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectivescited by 3
  10. 2024CryptoTrain: Fast Secure Training on Encrypted Datasetcited by 3
  11. 2021Fast Privacy-Preserving Text Classification based on Secure Multiparty Computationcited by 2
  12. 2024Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Trainingcited by 2
  13. 2021MPC-Friendly Commitments for Publicly Verifiable Covert Securitycited by 1
  14. 2022Towards Privacy-Preserving Neural Architecture Searchcited by 1
  15. 2023SelectFormer: Private and Practical Data Selection for Transformerscited by 1
  16. 2023Edge AI for Internet of Energy: Challenges and Perspectivescited by 1
  17. 2024Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumptioncited by 1
  18. 2024Privacy-Preserving Hierarchical Model-Distributed Inferencecited by 1
  19. 2025CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computationcited by 1
  20. 2021Round and Communication Balanced Protocols for Oblivious Evaluation of Finite State Machinescited by 0
  21. 2021PolyDNN: Polynomial Representation of NN for Communication-less SMPC Inferencecited by 0
  22. 2022Adversarial Representation Sharing: A Quantitative and Secure Collaborative Learning Frameworkcited by 0
  23. 2024Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attackcited by 0
  24. 2024Amalgam: A Framework for Obfuscated Neural Network Training on the Cloudcited by 0
  25. 2024Efficiently Achieving Secure Model Training and Secure Aggregation to Ensure Bidirectional Privacy-Preservation in Federated Learningcited by 0
  26. 2024CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inferencecited by 0
  27. 2025DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differencescited by 0
  28. 2025PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecturecited by 0
  29. 2026UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimizationcited by 0