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.
翻译:显而易见的推断使云层能够提供神经网络推断为服务(NN-IaaS),同时既不披露客户数据,也不披露服务器的模型。然而,在隐蔽推断下的隐私保障通常带来很高的效率和准确性成本。我们提议Popcorn,这是完全建立在Paillier同色加密计划的简洁、不为人知的推断框架。我们设计了一系列新协议,以计算非线激活和最大共享层。我们利用神经网络压缩技术(即神经重量调整和量化)加快推断计算。然而,为了实施爆米花框架,我们只需要用其相应的Paillierer同色操作取代现有网络的变相操作。我们首先根据MNIST和CIFAR-10的分类任务进行业绩评估和比较。比照现有解决方案,波摩公司带来了一个重大的通信间接扣减,并有一定的运行时间增长。然后,我们把现有网络的测算结果作为基准,我们用一个基于商业图像网络的升级数据来测量。