Open AccessRetracted: Convolutional neural network based on differential privacy in exponential attenuation mode for image classification
Author(s) -
Yang Jingjing,
Wu Jinzhao,
Wang Xiaojing
Publication year - 2020
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2020.0078
Subject(s) - differential privacy , convolutional neural network , attenuation , mnist database , computer science , gaussian noise , exponential function , artificial intelligence , noise (video) , artificial neural network , algorithm , mode (computer interface) , gaussian , deep learning , pattern recognition (psychology) , image (mathematics) , mathematics , physics , optics , mathematical analysis , quantum mechanics , operating system
Privacy information leaks have become a major problem hindering the development of the convolutional neural network and deep learning. Differential privacy protection has been applied to deep learning by more and more scholars to protect image training sets. The differentially private SGD (DP‐SGD) algorithm is adding Gaussian noise of a fixed level will cause the accuracy of the model to increase slowly with the increase of training times. To solve this problem, this study presents a convolutional neural network based on differential privacy in exponential attenuation mode. Firstly, the attenuation coefficient of Gaussian noise is linked with the training times and the accuracy of the model. Secondly, the DP‐SGD algorithm in exponential attenuation mode is proposed. The calculation method of the differential privacy protection budget in exponential attenuation mode is given. Finally, experiments with the MNIST dataset and X‐ray images verify the feasibility of using the original data of the Gaussian noise convolutional neural network based on differential privacy protection in exponential attenuation mode.