A Novel Privacy-Preserving Deep Learning Scheme without Using Cryptography Component

TL;DR

This paper introduces a new privacy-preserving deep learning scheme that secures data, output, and models without cryptography, leveraging DNN properties for efficiency and security in real-world applications.

Contribution

It presents a novel deep learning privacy scheme that avoids cryptography, utilizing DNN properties for secure training and inference.

Findings

The scheme effectively protects input, output, and model privacy.

Experimental results show high efficiency and practicality.

The method is secure against common threats.

Abstract

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.