Research and Application Path Analysis of Deep Learning Differential Privacy Protection Method Based on Multiple Data Sources

DOI

10.2991/978-94-6463-064-0_34How to use a DOI?

Keywords

Multiple data sources; Differential privacy; Deep learning; Aggregation; Deep Confidence Network

Abstract

The deep learning model will contain user-sensitive information during training. When the model is applied, the attacker can recover the sensitive information in the training data set through model inversion attacks, and directly or indirectly disclose the user-sensitive information. The existing methods can not solve the problem that the privacy budget accumulates with the increase of training times. This paper proposes a method of research on deep learning differential privacy protection method based on multiple data sources, aim at making privacy consumption independent of the number of training epochs to guarantee the potential to work with large datasets. First, we calculate the privacy budget upper bound to optimal experiment selection for parameter estimation. Second, we use the upper bound to determine the number of group, also to balance the number of group and the data size of the subdataset, avoiding data relying on a single model causes leakage of user sensitive information. Finally, we ensemble several models with majority voting, and perturb single model the traditional convolutional deep belief network (CDBN) objective functions, to descend the dependence of privacy budgets on the training deep learning model and improve machine learning results. We applied our model to a health social network dataset and MNIST dataset, and the results show that our method has high privacy protection ability than the existing method for sensitive information on the training dataset. Moreover, standardization can be a feasible path for the generalized application of the technique, which is beneficial for the stability of the application of differential privacy protection techniques and the subsequent feedback updates.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Junhua Chen
AU  - Yiming Liu
PY  - 2022
DA  - 2022/12/27
TI  - Research and Application Path Analysis of Deep Learning Differential Privacy Protection Method Based on Multiple Data Sources
BT  - Proceedings of the 2022 3rd International Conference on Big Data and Social Sciences (ICBDSS 2022)
PB  - Atlantis Press
SP  - 299
EP  - 310
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-064-0_34
DO  - 10.2991/978-94-6463-064-0_34
ID  - Chen2022
ER  -