Privacy Preserving Inference with Convolutional Neural Network Ensemble
Privacy Preserving Inference with Convolutional Neural Network Ensemble
复制标题
DOI：
10.1109/ipccc50635.2020.9391544
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Alexander Xiong;M. Nguyen;Andrew So;Tingting Chen
中科院分区：
文献类型：
--
作者：
Alexander Xiong;M. Nguyen;Andrew So;Tingting Chen
云上的机器学习即服务不仅提供了扩展苛刻工作负载的解决方案，而且还允许更广泛地利用经过训练的深度神经网络。例如，在医疗领域，基于云的深度学习辅助诊断可以挽救生命，特别是在缺乏经验丰富的医生和专业知识的发展中地区。然而，在使用云服务进行深度学习的同时保护最终用户的数据隐私是一个挑战。最近的一些基于全同态加密的工作使神经网络能够对加密的输入数据进行预测。在本文中，我们进一步扩展了隐私保护深度神经网络推理的能力，通过多个深度神经网络模型对加密数据进行联合决策，以解决不平衡的局部训练数据集引起的偏差。特别是，我们设计并实现了一个隐私保护预测方法，通过卷积神经网络的合奏。大量的实验结果表明，我们的方法可以达到更高的准确率相比，个别模型，并保持在同一水平的用户数据隐私。我们还验证了我们的实施的时间效率。
Machine Learning as a Service on cloud not only provides a solution to scale demanding workloads, but also allows broader accessibility for the utilization of trained deep neural networks. For example, in the medical field, cloud-based deep-learning assisted diagnoses can be life-saving, especially in developing areas where experienced doctors and domain expertise are lacking. However, preserving end-users' data privacy while using cloud service for deep learning is a challenge. Some recent works based on fully homomorphic encryption have enabled neural-network predictions on encrypted input data. In this paper, we further extend the capability of privacy preserving deep neural network inference, through a joint decision made by multiple deep neural network models on encrypted data, to address bias caused by unbalanced local training datasets. In particular, we design and implement a privacy preserving prediction method through an ensemble of convolutional neural networks. The extensive experiment results show that our method can achieve higher accuracy compared to individual models, and preserve the user data privacy at the same level. We also verify the time efficiency of our implementation.