mlsanityData to 7 Oct 2026

CrypTFlow: Secure TensorFlow Inference

arXiv 1909.07814 ↗First posted 16 Sep 2019cs.CR cs.LG cs.PLcited by 61

Not on the map. Why?

Abstract (arXiv)

We present CrypTFlow, a first of its kind system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build three components. Our first component, Athos, is an end-to-end compiler from TensorFlow to a variety of semi-honest MPC protocols. The second component, Porthos, is an improved semi-honest 3-party protocol that provides significant speedups for TensorFlow like applications. Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity guarantees to convert any semi-honest MPC protocol into an MPC protocol that provides malicious security. The malicious security of the protocols output by Aramis relies on integrity of the hardware and semi-honest security of MPC. Moreover, our system matches the inference accuracy of plaintext TensorFlow. We experimentally demonstrate the power of our system by showing the secure inference of real-world neural networks such as ResNet50 and DenseNet121 over the ImageNet dataset with running times of about 30 seconds for semi-honest security and under two minutes for malicious security. Prior work in the area of secure inference has been limited to semi-honest security of small networks over tiny datasets such as MNIST or CIFAR. Even on MNIST/CIFAR, CrypTFlow outperforms prior work.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 12; 2023: 13; 2024: 10; 2025: 8; 2026: 3.

61 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  3. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  4. 2022Scaling up Trustless DNN Inference with Zero-Knowledge Proofscited by 30
  5. 2021SIRNN: A Math Library for Secure RNN Inferencecited by 28
  6. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  7. 2022pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testingcited by 20
  8. 2022Exploiting Data Sparsity in Secure Cross-Platform Social Recommendationcited by 17
  9. 2022Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realizationcited by 16
  10. 2023Bytes Are All You Need: Transformers Operating Directly On File Bytescited by 16
  11. 2024Trustless Audits without Revealing Data or Modelscited by 14
  12. 2021secureTF: A Secure TensorFlow Frameworkcited by 12
38 more
  1. 2021Privacy-Preserving Feature Selection with Secure Multiparty Computationcited by 12
  2. 2023RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inferencecited by 12
  3. 2021Privacy-Preserving Video Classification with Convolutional Neural Networkscited by 10
  4. 2022SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Servicecited by 10
  5. 2023HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networkscited by 9
  6. 2025TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networkscited by 9
  7. 2023A Survey of Secure Computation Using Trusted Execution Environmentscited by 8
  8. 2021Enabling Homomorphically Encrypted Inference for Large DNN Modelscited by 6
  9. 2021Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutationcited by 5
  10. 2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
  11. 2023GPU-based Private Information Retrieval for On-Device Machine Learning Inferencecited by 5
  12. 2023Improving Heterogeneous Model Reuse by Density Estimationcited by 5
  13. 2023Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inferencecited by 5
  14. 2024MPC-Minimized Secure LLM Inferencecited by 5
  15. 2021Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimationcited by 4
  16. 2022MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inferencecited by 4
  17. 2024SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloudcited by 3
  18. 2024CipherDM: Secure Three-Party Inference for Diffusion Model Samplingcited by 3
  19. 2025Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsitycited by 3
  20. 2021Fast Privacy-Preserving Text Classification based on Secure Multiparty Computationcited by 2
  21. 2021Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Supportcited by 2
  22. 2022Securing the Classification of COVID-19 in Chest X-ray Images: A Privacy-Preserving Deep Learning Approachcited by 2
  23. 2022Efficient ML Models for Practical Secure Inferencecited by 2
  24. 2022PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inferencecited by 2
  25. 2023Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuitscited by 2
  26. 2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
  27. 2024HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inferencecited by 2
  28. 2022Private Multiparty Perception for Navigationcited by 1
  29. 2023Securing Neural Networks with Knapsack Optimizationcited by 1
  30. 2023Towards Fast and Scalable Private Inferencecited by 1
  31. 2023Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chainscited by 1
  32. 2024Secure Federated Learning Approaches to Diagnosing COVID-19cited by 1
  33. 2024Privacy-Preserving Hierarchical Model-Distributed Inferencecited by 1
  34. 2024PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimizationcited by 1
  35. 2025Covert Attacks on Machine Learning Training in Passively Secure MPCcited by 1
  36. 2025Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applicationscited by 1
  37. 2025CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computationcited by 1
  38. 2026Fine-Tuning Integrity for Modern Neural Networks: Structured Drift Proofs via Norm, Rank, and Sparsity Certificatescited by 1

50 most cited of 61 All 61 (JSON)