CBNN实现高效安全的二值神经网络推理，三方可协作保护隐私。
CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
- 三方安全计算框架，用知识蒸馏和可分离卷积改造传统二值网络
- 支持加密线性与非线性运算，推理效率高且准确率保持良好
- 适合需要隐私保护的边缘设备或云上模型部署场景
二值神经网络（BNN）通过二值运算提升计算效率，有助于实现隐私保护机器学习（PPML）。然而在实际应用中仍面临通信开销大、精度下降等问题。本文提出CBNN，一种面向定制化二值神经网络推理的三方安全计算框架。通过知识蒸馏与可分离卷积，将标准BNN转化为适用于多方计算（MPC）的定制化BNN，保持高实用性。采用优化的协议实现基础操作的安全推理：在线性运算中引入复制秘密共享与MPC友好的卷积结构，在非线性运算中设计新型安全激活函数。实验表明，经过定制化二值化与安全机制后，多个典型BNN模型仍能保持优异性能。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。