Privacy-preserving deep neural networks have become essential and have attracted the attention of many researchers due to the need to maintain the privacy and the confidentiality of personal and sensitive data. The importance of privacy-preserving networks has increased with the widespread use of neural networks as a service in unsecured cloud environments. Different methods have been proposed and developed to solve the privacy-preserving problem using deep neural networks on encrypted data. In this article, we reviewed some of the most relevant and well-known computational and perceptual image encryption methods. These methods as well as their results have been presented, compared, and the conditions of their use, the durability and robustness of some of them against attacks, have been discussed. Some of the mentioned methods have demonstrated an ability to hide information and make it difficult for adversaries to retrieve it while maintaining high classification accuracy. Based on the obtained results, it was suggested to develop and use some of the cited privacy-preserving methods in applications other than classification.
The secure scalar product protocol is widely applied to solve practical problems such as privacy-preserving data mining, secure auction, secure electronic voting, privacy-preserving recommendation system, privacy-preserving statistical data analysis, etc.. In this paper, we propose an efficient multi-party secure computation protocol using Elliptic curve cryptography, which allows to compute the sum value of multi-scalar products without revealing about the input vectors. Moreover, theoretical and experimental analysis shows that the proposed method is more efficient than others in both computation and communication.
Privacy-Preserving Deep Neural Network Methods: Computational and Perceptual Methods—An Overview
