mlsanityData to 14 Oct 2026

CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference

arXiv 2412.16449 ↗First posted 21 Dec 2024cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Binarized Neural Networks (BNN) offer efficient implementations for machine learning tasks and facilitate Privacy-Preserving Machine Learning (PPML) by simplifying operations with binary values. Nevertheless, challenges persist in terms of communication and accuracy in their application scenarios. In this work, we introduce CBNN, a three-party secure computation framework tailored for efficient BNN inference. Leveraging knowledge distillation and separable convolutions, CBNN transforms standard BNNs into MPC-friendly customized BNNs, maintaining high utility. It performs secure inference using optimized protocols for basic operations. Specifically, CBNN enhances linear operations with replicated secret sharing and MPC-friendly convolutions, while introducing a novel secure activation function to optimize non-linear operations. We demonstrate the effectiveness of CBNN by transforming and securely implementing several typical BNN models. Experimental results indicate that CBNN maintains impressive performance even after customized binarization and security measures

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 21 Dec 2024.

Builds on

16 of 35 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  5. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  6. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  7. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  8. 2020CrypTFlow2: Practical 2-Party Secure Inferencecited by 82
  9. 2020FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learningcited by 74
  10. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
  11. 2019XONN: XNOR-based Oblivious Deep Neural Network Inferencecited by 51
  12. 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
4 more
  1. 2019QUOTIENT: Two-Party Secure Neural Network Training and Predictioncited by 41
  2. 2015Do We Need More Training Data?cited by 27
  3. 2019Secure Evaluation of Quantized Neural Networkscited by 22
  4. 2019nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Datacited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient and Encrypted Inference using Binarized Neural Networks within In-Memory Computing Architectures
  2. 2025SecONNds: Secure Outsourced Neural Network Inference on ImageNet
  3. 2025Efficient Certified Reasoning for Binarized Neural Networks
  4. 2024Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference
  5. 2021"BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
  6. 2026Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference
  7. 2024Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization
  8. 2025On Integer Programming for the Binarized Neural Network Verification Problem