arXiv 2107.017862021-07-12cs.CR

Popcorn：Paillier满足高效不经意神经网络推理的压缩

Popcorn: Paillier Meets Compression For Efficient Oblivious Neural Network Inference

Jun Wang, Chao Jin, Souhail Meftah, Khin Mi Mi Aung

备注：: This version corrects a naive but significant typo in Table 8 in our previous version. Previously, we mistakenly indicated the communication cost in COM(g), i.e., communication bandwidth in gigabyte. In fact, it should be COM as in this version, and COM presents the communication bandwidth in megabyte. It is megabyte, not gigabyte

摘要：

不经意推理使云能够提供神经网络推理即服务（NN-IaaS），同时既不泄露客户端数据，也不泄露服务器的模型。然而，不经意推理下的隐私保证通常会带来效率和准确性的沉重代价。我们提出爆米花，一个简洁的不经意的推理框架完全建立在Paillier同态加密计划。我们设计了一套新的协议来计算非线性激活和最大池层。我们利用神经网络压缩技术（即，神经权重修剪和量化）以加速推理计算。为了实现Popcorn框架，我们只需要将现有网络的代数运算替换为相应的Paillier同态运算，这对于工程开发非常友好。我们首先进行性能评估和比较的基础上MNIST和CIFAR-10分类任务。与现有解决方案相比，Popcorn带来了显着的通信开销减少，具有适度的运行时间增加。然后，我们在ImageNet上测试了不经意推理的性能。据我们所知，这是第一份基于商业级数据集的报告，向生产部署迈出了一步。

英文摘要：

Oblivious inference enables the cloud to provide neural network inference-as-a-service (NN-IaaS), whilst neither disclosing the client data nor revealing the server's model. However, the privacy guarantee under oblivious inference usually comes with a heavy cost of efficiency and accuracy. We propose Popcorn, a concise oblivious inference framework entirely built on the Paillier homomorphic encryption scheme. We design a suite of novel protocols to compute non-linear activation and max-pooling layers. We leverage neural network compression techniques (i.e., neural weights pruning and quantization) to accelerate the inference computation. To implement the Popcorn framework, we only need to replace algebraic operations of existing networks with their corresponding Paillier homomorphic operations, which is extremely friendly for engineering development. We first conduct the performance evaluation and comparison based on the MNIST and CIFAR-10 classification tasks. Compared with existing solutions, Popcorn brings a significant communication overhead deduction, with a moderate runtime increase. Then, we benchmark the performance of oblivious inference on ImageNet. To our best knowledge, this is the first report based on a commercial-level dataset, taking a step towards the deployment to production.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。