mlsanityData to 7 Oct 2026

CrypTen: Secure Multi-Party Computation Meets Machine Learning

arXiv 2109.00984 ↗First posted 2 Sep 2021cs.LG cs.CRcited by 131

Not on the map. Why?

Abstract (arXiv)

Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: it facilitates training of machine-learning models on private data sets owned by different parties, evaluation of one party's private model using another party's private data, etc. Although a range of studies implement machine-learning models via secure MPC, such implementations are not yet mainstream. Adoption of secure MPC is hampered by the absence of flexible software frameworks that "speak the language" of machine-learning researchers and engineers. To foster adoption of secure MPC in machine learning, we present CrypTen: a software framework that exposes popular secure MPC primitives via abstractions that are common in modern machine-learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks. This paper describes the design of CrypTen and measure its performance on state-of-the-art models for text classification, speech recognition, and image classification. Our benchmarks show that CrypTen's GPU support and high-performance communication between (an arbitrary number of) parties allows it to perform efficient private evaluation of modern machine-learning models under a semi-honest threat model. For example, two parties using CrypTen can securely predict phonemes in speech recordings using Wav2Letter faster than real-time. We hope that CrypTen will spur adoption of secure MPC in the machine-learning community.

Key facts. Cited by 131 papers in the map (data through 7 Oct 2026). Builds on 25 of its 83 references that are in the map. First posted on arXiv 2 Sep 2021.

Builds on

25 of 83 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  8. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  10. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  11. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  12. 2020The Discrete Gaussian for Differential Privacycited by 134
13 more
  1. 2018A generic framework for privacy preserving deep learningcited by 103
  2. 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
  3. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
  4. 2019CrypTFlow: Secure TensorFlow Inferencecited by 61
  5. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  6. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  7. 2016Wav2Letter: an End-to-End ConvNet-based Speech Recognition Systemcited by 43
  8. 2020BLAZE: Blazing Fast Privacy-Preserving Machine Learningcited by 32
  9. 2019Trident: Efficient 4PC Framework for Privacy Preserving Machine Learningcited by 26
  10. 2019TensorFlow Eager: A Multi-Stage, Python-Embedded DSL for Machine Learningcited by 22
  11. 2019ASTRA: High Throughput 3PC over Rings with Application to Secure Predictioncited by 18
  12. 2020Secure multiparty computations in floating-point arithmeticcited by 8
  13. 2020A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 24; 2023: 28; 2024: 30; 2025: 23; 2026: 20.

131 papers.

Sort:

By area:

  1. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  2. 2022Transformers in Medical Imaging: A Surveycited by 245
  3. 2021Trustworthy AI: From Principles to Practicescited by 206
  4. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 83
  5. 2022MPCFormer: fast, performant and private Transformer inference with MPCcited by 67
  6. 2022Scaling up Trustless DNN Inference with Zero-Knowledge Proofscited by 30
  7. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  8. 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 26
  9. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  10. 2023AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMscited by 21
  11. 2025A Survey of Zero-Knowledge Proof Based Verifiable Machine Learningcited by 21
  12. 2023LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformerscited by 20
38 more
  1. 2022MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attentioncited by 19
  2. 2022Differential Privacy Guarantees for Stochastic Gradient Langevin Dynamicscited by 18
  3. 2026Intelligent AI Delegationcited by 16
  4. 2022Secure Aggregation for Federated Learning in Flowercited by 15
  5. 2023AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHEcited by 15
  6. 2024AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computingcited by 15
  7. 2024Nimbus: Secure and Efficient Two-Party Inference for Transformerscited by 15
  8. 2023Challenges and Remedies to Privacy and Security in AIGC: Exploring the Potential of Privacy Computing, Blockchain, and Beyondcited by 14
  9. 2024Verifiable evaluations of machine learning models using zkSNARKscited by 14
  10. 2024Trustless Audits without Revealing Data or Modelscited by 14
  11. 2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 13
  12. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  13. 2023RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inferencecited by 12
  14. 2022Robust Split Federated Learning for U-shaped Medical Image Networkscited by 11
  15. 2022SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Servicecited by 10
  16. 2022HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learningcited by 10
  17. 2024A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directionscited by 10
  18. 2025TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networkscited by 9
  19. 2023MERGE: Fast Private Text Generationcited by 8
  20. 2023Blind quantum machine learning with quantum bipartite correlatorcited by 8
  21. 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacycited by 7
  22. 2024SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPCcited by 7
  23. 2024Comet: A Communication-efficient and Performant Approximation for Private Transformer Inferencecited by 7
  24. 2021Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classificationcited by 6
  25. 2023Balancing Privacy Protection and Interpretability in Federated Learningcited by 6
  26. 2024CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inferencecited by 6
  27. 2025Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systemscited by 6
  28. 2023GPU-based Private Information Retrieval for On-Device Machine Learning Inferencecited by 5
  29. 2023Improving Heterogeneous Model Reuse by Density Estimationcited by 5
  30. 2023Attesting Distributional Properties of Training Data for Machine Learningcited by 5
  31. 2024MPC-Minimized Secure LLM Inferencecited by 5
  32. 2025Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEscited by 5
  33. 2022MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inferencecited by 4
  34. 2022Hijack Vertical Federated Learning Models As One Partycited by 4
  35. 2023Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functionscited by 4
  36. 2024ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasetscited by 4
  37. 2024Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloudcited by 4
  38. 2021PRECAD: Privacy-Preserving and Robust Federated Learning via Crypto-Aided Differential Privacycited by 3

50 most cited of 131 All 131 (JSON)