mlsanityData to 7 Oct 2026

Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption

arXiv 2202.13351 ↗First posted 27 Feb 2022cs.CR cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

This work presents a novel protocol for fast secure inference of neural networks applied to computer vision applications. It focuses on improving the overall performance of the online execution by deploying a subset of the model weights in plaintext on the client's machine, in the fashion of SplitNNs. We evaluate our protocol on benchmark neural networks trained on the CIFAR-10 dataset using SEAL via TenSEAL and discuss runtime and security performances. Empirical security evaluation using Membership Inference and Model Extraction attacks showed that the protocol was more resilient under the same attacks than a similar approach also based on SplitNN. When compared to related work, we demonstrate improvements of 2.5x-10x for the inference time and 14x-290x in communication costs.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 27 Feb 2022.

Builds on

17 of 26 references.

References · 17

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016Deep Learning with Differential Privacycited by 2,682
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2017Deep Layer Aggregationcited by 436
  6. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 391
  7. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  8. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  9. 2020Data-Free Model Extractioncited by 121
  10. 2020Unleashing the Tiger: Inference Attacks on Split Learningcited by 104
  11. 2020CrypTFlow2: Practical 2-Party Secure Inferencecited by 82
  12. 2020NoPeek: Information leakage reduction to share activations in distributed deep learningcited by 66
5 more
  1. 2020Cryptanalytic Extraction of Neural Network Modelscited by 65
  2. 2021TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryptioncited by 51
  3. 2020DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networkscited by 23
  4. 2021Intel HEXL: Accelerating Homomorphic Encryption with Intel AVX512-IFMA52cited by 8
  5. 2021Syft 0.5: A Platform for Universally Deployable Structured Transparencycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 0; 2026: 2.

9 papers.

  1. 2023Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attackscited by 8
  2. 2023Split Without a Leak: Reducing Privacy Leakage in Split Learningcited by 6
  3. 2023SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detectioncited by 4
  4. 2024Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMixcited by 2
  5. 2024Training on Fake Labels: Mitigating Label Leakage in Split Learning via Secure Dimension Transformationcited by 2
  6. 2023Compact: Approximating Complex Activation Functions for Secure Computationcited by 1
  7. 2026The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Modelscited by 1
  8. 2023GAN-based Vertical Federated Learning for Label Protection in Binary Classificationcited by 0
  9. 2026SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacycited by 0