Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering
As a social information product, the privacy and usability of high-dimensional data are the core issues in the field of privacy protection. Feature selection is a commonly used dimensionality reduction processing technique for high-dimensional data. Some feature selection methods only process some o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/9/1959 |
| _version_ | 1797602751283200000 |
|---|---|
| author | Zhiguang Chu Jingsha He Xiaolei Zhang Xing Zhang Nafei Zhu |
| author_facet | Zhiguang Chu Jingsha He Xiaolei Zhang Xing Zhang Nafei Zhu |
| author_sort | Zhiguang Chu |
| collection | DOAJ |
| description | As a social information product, the privacy and usability of high-dimensional data are the core issues in the field of privacy protection. Feature selection is a commonly used dimensionality reduction processing technique for high-dimensional data. Some feature selection methods only process some of the features selected by the algorithm and do not take into account the information associated with the selected features, resulting in the usability of the final experimental results not being high. This paper proposes a hybrid method based on feature selection and a cluster analysis to solve the data utility and privacy problems of high-dimensional data in the actual publishing process. The proposed method is divided into three stages: (1) screening features; (2) analyzing the clustering of features; and (3) adaptive noise. This paper uses the Wisconsin Breast Cancer Diagnostic (WDBC) database from UCI’s Machine Learning Library. Using classification accuracy to evaluate the performance of the proposed method, the experiments show that the original data are processed by the algorithm in this paper while protecting the sensitive data information while retaining the contribution of the data to the diagnostic results. |
| first_indexed | 2024-03-11T04:21:04Z |
| format | Article |
| id | doaj.art-51016bffe9144e3599689d38d2c0b186 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T04:21:04Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-51016bffe9144e3599689d38d2c0b1862023-11-17T22:46:49ZengMDPI AGElectronics2079-92922023-04-01129195910.3390/electronics12091959Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and ClusteringZhiguang Chu0Jingsha He1Xiaolei Zhang2Xing Zhang3Nafei Zhu4School of Software Engineering, Beijing University of Technology, Beijing 100124, ChinaSchool of Software Engineering, Beijing University of Technology, Beijing 100124, ChinaKey Laboratory of Security for Network and Data in Industrial Internet of Liaoning Province, Jinzhou 121000, ChinaKey Laboratory of Security for Network and Data in Industrial Internet of Liaoning Province, Jinzhou 121000, ChinaSchool of Software Engineering, Beijing University of Technology, Beijing 100124, ChinaAs a social information product, the privacy and usability of high-dimensional data are the core issues in the field of privacy protection. Feature selection is a commonly used dimensionality reduction processing technique for high-dimensional data. Some feature selection methods only process some of the features selected by the algorithm and do not take into account the information associated with the selected features, resulting in the usability of the final experimental results not being high. This paper proposes a hybrid method based on feature selection and a cluster analysis to solve the data utility and privacy problems of high-dimensional data in the actual publishing process. The proposed method is divided into three stages: (1) screening features; (2) analyzing the clustering of features; and (3) adaptive noise. This paper uses the Wisconsin Breast Cancer Diagnostic (WDBC) database from UCI’s Machine Learning Library. Using classification accuracy to evaluate the performance of the proposed method, the experiments show that the original data are processed by the algorithm in this paper while protecting the sensitive data information while retaining the contribution of the data to the diagnostic results.https://www.mdpi.com/2079-9292/12/9/1959high-dimensional datafeature selectionrandom forestclusteringdifferential privacy |
| spellingShingle | Zhiguang Chu Jingsha He Xiaolei Zhang Xing Zhang Nafei Zhu Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering Electronics high-dimensional data feature selection random forest clustering differential privacy |
| title | Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering |
| title_full | Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering |
| title_fullStr | Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering |
| title_full_unstemmed | Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering |
| title_short | Differential Privacy High-Dimensional Data Publishing Based on Feature Selection and Clustering |
| title_sort | differential privacy high dimensional data publishing based on feature selection and clustering |
| topic | high-dimensional data feature selection random forest clustering differential privacy |
| url | https://www.mdpi.com/2079-9292/12/9/1959 |
| work_keys_str_mv | AT zhiguangchu differentialprivacyhighdimensionaldatapublishingbasedonfeatureselectionandclustering AT jingshahe differentialprivacyhighdimensionaldatapublishingbasedonfeatureselectionandclustering AT xiaoleizhang differentialprivacyhighdimensionaldatapublishingbasedonfeatureselectionandclustering AT xingzhang differentialprivacyhighdimensionaldatapublishingbasedonfeatureselectionandclustering AT nafeizhu differentialprivacyhighdimensionaldatapublishingbasedonfeatureselectionandclustering |