mlsanityData to 14 Oct 2026

Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption

arXiv 2304.14836 ↗First posted 26 Apr 2023cs.LG cs.AI cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Training large-scale CNNs that during inference can be run under Homomorphic Encryption (HE) is challenging due to the need to use only polynomial operations. This limits HE-based solutions adoption. We address this challenge and pioneer in providing a novel training method for large polynomial CNNs such as ResNet-152 and ConvNeXt models, and achieve promising accuracy on encrypted samples on large-scale dataset such as ImageNet. Additionally, we provide optimization insights regarding activation functions and skip-connection latency impacts, enhancing HE-based evaluation efficiency. Finally, to demonstrate the robustness of our method, we provide a polynomial adaptation of the CLIP model for secure zero-shot prediction, unlocking unprecedented capabilities at the intersection of HE and transfer learning.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 37 of its 73 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

37 of 73 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2022A ConvNet for the 2020scited by 3,579
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  8. 2016Wide Residual Networkscited by 3,070
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  10. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  11. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  12. 2016Resnet in Resnet: Generalizing Residual Architecturescited by 110
25 more
  1. 2020CrypTFlow2: Practical 2-Party Secure Inferencecited by 82
  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. 2021Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Networkcited by 57
  5. 2017CryptoDL: Deep Neural Networks over Encrypted Datacited by 56
  6. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  7. 2021DeepReDuce: ReLU Reduction for Fast Private Inferencecited by 50
  8. 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
  9. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  10. 2020CryptoNAS: Private Inference on a ReLU Budgetcited by 40
  11. 2020Pi-nets: Deep Polynomial Neural Networkscited by 39
  12. 2021Precise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Datacited by 27
  13. 2021HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecturecited by 24
  14. 2020HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Datacited by 22
  15. 2019nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Datacited by 21
  16. 2020ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharingcited by 20
  17. 2021Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learningcited by 14
  18. 2021GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networkscited by 10
  19. 2021A methodology for training homomorphicencryption friendly neural networkscited by 10
  20. 2022Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryptioncited by 9
  21. 2023HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networkscited by 9
  22. 2020AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inferencecited by 7
  23. 2021Enabling Homomorphically Encrypted Inference for Large DNN Modelscited by 6
  24. 2019Privacy preserving Neural Network Inference on Encrypted Data with GPUscited by 4
  25. 2021SoK: Privacy-preserving Deep Learning with Homomorphic Encryptioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2024Encryption-Friendly LLM Architecturecited by 17
  2. 2024Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvementcited by 1
  3. 2025Peregrine: One-Shot Fine-Tuning for FHE Inference of General Deep CNNscited by 1
  4. 2023High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertextscited by 0
  5. 2026HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptationcited by 0