Adaptive Differential Privacy Mechanism Based on Entropy Theory for Preserving Deep Neural Networks

Xiangfei Zhang, Feng Yang, Yu Guo, Hang Yu, Zhengxia Wang and Qingchen Zhang ()
Additional contact information
Xiangfei Zhang: School of Cyberspace Security, Hainan University, Haikou 570228, China
Feng Yang: School of Computer Science and Technology, Hainan University, Haikou 570228, China
Yu Guo: School of Computer Science and Technology, Hainan University, Haikou 570228, China
Hang Yu: School of Computer Science and Technology, Hainan University, Haikou 570228, China
Zhengxia Wang: School of Computer Science and Technology, Hainan University, Haikou 570228, China
Qingchen Zhang: School of Computer Science and Technology, Hainan University, Haikou 570228, China

Mathematics, 2023, vol. 11, issue 2, 1-11

Abstract: Recently, deep neural networks (DNNs) have achieved exciting things in many fields. However, the DNN models have been proven to divulge privacy, so it is imperative to protect the private information of the models. Differential privacy is a promising method to provide privacy protection for DNNs. However, existing DNN models based on differential privacy protection usually inject the same level of noise into parameters, which may lead to a balance between model performance and privacy protection. In this paper, we propose an adaptive differential privacy scheme based on entropy theory for training DNNs, with the aim of giving consideration to the model performance and protecting the private information in the training data. The proposed scheme perturbs the gradients according to the information gain of neurons during training, that is, in the process of back propagation, less noise is added to neurons with larger information gain, and vice-versa. Rigorous experiments conducted on two real datasets demonstrate that the proposed scheme is highly effective and outperforms existing solutions.

Keywords: deep neural networks; differential privacy; Laplace noise (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/2/330/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/2/330/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:2:p:330-:d:1029082

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().