Open Access
ARTICLE
An Explanatory Strategy for Reducing the Risk of Privacy Leaks
Mingting Liu1, Xiaozhang Liu1,*, Anli Yan1, Xiulai Li1,2, Gengquan Xie1, Xin Tang3
1 Hainan University, Haikou, 570228, China
2 Hainan Hairui Zhong Chuang Technol Co., Ltd., Haikou, 570228, China
3 School of Electrical and Electronic Engineering, Nanyang Technological University, 639798, Singapore
* Corresponding Author: Xiaozhang Liu. Email:
Journal of Information Hiding and Privacy Protection 2021, 3(4), 181-192. https://doi.org/10.32604/jihpp.2021.027385
Received 16 January 2022; Accepted 25 February 2022; Issue published 22 March 2022
Abstract
As machine learning moves into high-risk and sensitive applications
such as medical care, autonomous driving, and financial planning, how to
interpret the predictions of the black-box model becomes the key to whether
people can trust machine learning decisions. Interpretability relies on providing
users with additional information or explanations to improve model transparency
and help users understand model decisions. However, these information
inevitably leads to the dataset or model into the risk of privacy leaks. We
propose a strategy to reduce model privacy leakage for instance interpretability
techniques. The following is the specific operation process. Firstly, the user
inputs data into the model, and the model calculates the prediction confidence of
the data provided by the user and gives the prediction results. Meanwhile, the
model obtains the prediction confidence of the interpretation data set. Finally, the
data with the smallest Euclidean distance between the confidence of the
interpretation set and the prediction data as the explainable data. Experimental
results show that The Euclidean distance between the confidence of
interpretation data and the confidence of prediction data provided by this method
is very small, which shows that the model's prediction of interpreted data is very
similar to the model's prediction of user data. Finally, we demonstrate the
accuracy of the explanatory data. We measure the matching degree between the
real label and the predicted label of the interpreted data and the applicability to
the network model. The results show that the interpretation method has high
accuracy and wide applicability.
Keywords
Cite This Article
M. Liu, X. Liu, A. Yan, X. Li, G. Xie
et al., "An explanatory strategy for reducing the risk of privacy leaks,"
Journal of Information Hiding and Privacy Protection, vol. 3, no.4, pp. 181–192, 2021. https://doi.org/10.32604/jihpp.2021.027385