A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component
This addresses privacy concerns for customers and service providers in deep learning applications, but appears incremental as it builds on existing neural network properties without introducing a new paradigm.
The paper tackles the problem of privacy in deep learning by proposing a novel privacy-preserving model and secure training/inference scheme that protects input, output, and model without using cryptography, with experimental results showing it is efficient and suitable for real applications.
Recently, deep learning, which uses Deep Neural Networks (DNN), plays an important role in many fields. A secure neural network model with a secure training/inference scheme is indispensable to many applications. To accomplish such a task usually needs one of the entities (the customer or the service provider) to provide private information (customer's data or the model) to the other. Without a secure scheme and the mutual trust between the service providers and their customers, it will be an impossible mission. In this paper, we propose a novel privacy-preserving deep learning model and a secure training/inference scheme to protect the input, the output, and the model in the application of the neural network. We utilize the innate properties of a deep neural network to design a secure mechanism without using any complicated cryptography component. The security analysis shows our proposed scheme is secure and the experimental results also demonstrate that our method is very efficient and suitable for real applications.