论文标题
拆分HE：快速安全推理结合分裂学习和同形加密
Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption
论文作者
论文摘要
这项工作为应用于计算机视觉应用的神经网络的快速安全推断提供了一种新颖的协议。它专注于以Splitnns的方式在客户机器上以纯文本部署模型权重的子集来提高在线执行的整体性能。我们使用张力通过张力来评估在CIFAR-10数据集上训练的基准神经网络上的协议，并讨论运行时和安全性能。使用成员推理和模型提取攻击的经验安全评估表明，在相同攻击下，该协议比基于SplitNN的类似方法更具弹性。与相关工作相比，我们证明了推理时间的2.5倍 - 10倍和通信成本的14x-290x。
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.
