让神经网络在加密数据上运行，实现隐私保护下的高精度推理。
An End-to-End Homomorphically Encrypted Neural Network
- 用同态加密构建端到端神经网络，直接处理密文输入。
- 在情感分析任务中达到原始模型82.5%的准确率，同时保障全链路安全。
- 创新设计可微软化最大值层，提升加密激活熵，增强安全性。
当前主流神经网络均需明文输入，存在严重隐私风险。本文提出基于同态加密的端到端神经网络架构（HNN），可在加密数据上直接运算，实现完整隐私与安全。引入新型可微软化最大值（Differentiable Soft-Argmax）层，使输出logits在密文域可校准，提升激活参数熵值，增强模型安全性，同时保持整体噪声在可接受范围内。实验基于斯坦福情感树库（SST-2）数据集，使用微调后的DistilBERT base uncased模型进行测试，结果表明HNN模型在保证隐私的前提下，准确率可达原始模型的82.5%。
原文摘要 · Abstract (English)
Every commercially available, state-of-the-art neural network consume plain input data, which is a well-known privacy concern. We propose a new architecture based on homomorphic encryption, which allows the neural network to operate on encrypted data. We show that Homomorphic Neural Networks (HNN) can achieve full privacy and security while maintaining levels of accuracy comparable to plain neural networks. We also introduce a new layer, the Differentiable Soft-Argmax, which allows the calibration of output logits in the encrypted domain, raising the entropy of the activation parameters, thus improving the security of the model, while keeping the overall noise below the acceptable noise budget. Experiments were conducted using the Stanford Sentiment Treebank (SST-2) corpora on the DistilBERT base uncased finetuned SST-2 English sentiment analysis model, and the results show that the HNN model can achieve up to 82.5% of the accuracy of the plain model while maintaining full privacy and security.
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。