mlsanityData to 14 Oct 2026

Low Latency Privacy Preserving Inference

arXiv 1812.10659 ↗First posted 27 Dec 2018cs.LG stat.MLcited by 57

Not on the map. Why?

Abstract (arXiv)

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while protecting against information leakage. However, these methods are limited by the width and depth of neural networks that can be used (and hence the accuracy) and exhibit high latency even for relatively simple networks. In this study we provide two solutions that address these limitations. In the first solution, we present more than 10× improvement in latency and enable inference on wider networks compared to prior attempts with the same level of security. The improved performance is achieved by novel methods to represent the data during the computation. In the second solution, we apply the method of transfer learning to provide private inference services using deep networks with latency of ~0.16 seconds. We demonstrate the efficacy of our methods on several computer vision tasks.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 9; 2023: 10; 2024: 8; 2025: 9; 2026: 10.

57 papers.

Sort:

  1. 2021A Study of Face Obfuscation in ImageNetcited by 83
  2. 2021Biometrics: Trust, but Verifycited by 39
  3. 2023AutoReP: Automatic ReLU Replacement for Fast Private Network Inferencecited by 29
  4. 2023LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inferencecited by 27
  5. 2024Nimbus: Secure and Efficient Two-Party Inference for Transformerscited by 16
  6. 2023AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHEcited by 15
  7. 2022CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inferencecited by 10
  8. 2022ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipelinecited by 10
  9. 2021Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspectivecited by 9
  10. 2023HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networkscited by 9
  11. 2022Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representationscited by 7
  12. 2022Private and Reliable Neural Network Inferencecited by 7
38 more
  1. 2021Enabling Homomorphically Encrypted Inference for Large DNN Modelscited by 6
  2. 2022Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)cited by 5
  3. 2022Cluster Based Secure Multi-Party Computation in Federated Learning for Histopathology Imagescited by 4
  4. 2022Audit and Improve Robustness of Private Neural Networks on Encrypted Datacited by 4
  5. 2023TT-TFHE: a Torus Fully Homomorphic Encryption-Friendly Neural Network Architecturecited by 4
  6. 2021SoK: Privacy-preserving Deep Learning with Homomorphic Encryptioncited by 3
  7. 2025Leveraging ASIC AI Chips for Homomorphic Encryptioncited by 3
  8. 2025A Training Framework for Optimal and Stable Training of Polynomial Neural Networkscited by 3
  9. 2021Application of Homomorphic Encryption in Medical Imagingcited by 2
  10. 2023Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Servicecited by 2
  11. 2025CryptoFace: End-to-End Encrypted Face Recognitioncited by 2
  12. 2021Efficient CNN Building Blocks for Encrypted Datacited by 1
  13. 2021FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Datacited by 1
  14. 2021Efficient Encrypted Inference on Ensembles of Decision Treescited by 1
  15. 2021Enabling Inference Privacy with Adaptive Noise Injectioncited by 1
  16. 2023On Achieving Privacy-Preserving State-of-the-Art Edge Intelligencecited by 1
  17. 2023HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx modelscited by 1
  18. 2024Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inferencecited by 1
  19. 2024Privacy-Preserving Hierarchical Model-Distributed Inferencecited by 1
  20. 2024DCT-CryptoNets: Scaling Private Inference in the Frequency Domaincited by 1
  21. 2024Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Launderingcited by 1
  22. 2025SoK: Data Minimization in Machine Learningcited by 1
  23. 2026Manipulation-Proof Oblivious Audits against Deceptive Model Providerscited by 1
  24. 2021Efficient privacy-preserving inference for convolutional neural networkscited by 0
  25. 2022SEEK: model extraction attack against hybrid secure inference protocolscited by 0
  26. 2022Privacy-Preserving Credit Card Fraud Detection using Homomorphic Encryptioncited by 0
  27. 2023High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertextscited by 0
  28. 2023Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learningcited by 0
  29. 2024Speed-up of Data Analysis with Kernel Trick in Encrypted Domaincited by 0
  30. 2024Efficient Privacy-Preserving KAN Inference Using Homomorphic Encryptioncited by 0
  31. 2024Privacy-Preserving Verifiable Neural Network Inference Servicecited by 0
  32. 2025SecPE: Secure Prompt Ensembling for Private and Robust Large Language Modelscited by 0
  33. 2025Securing Transfer-Learned Networks with Reverse Homomorphic Encryptioncited by 0
  34. 2025Practical and Private Hybrid ML Inference with Fully Homomorphic Encryptioncited by 0
  35. 2025EP-HDC: Hyperdimensional Computing with Encrypted Parameters for High-Throughput Privacy-Preserving Inferencecited by 0
  36. 2025FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHEcited by 0
  37. 2026RobPI: Robust Private Inference against Malicious Clientcited by 0
  38. 2026Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learningcited by 0

50 most cited of 57 All 57 (JSON)