Research on Privacy Protection of Dynamic Dataset Republication Based on Local Modularity

With the emergence and development of a large number of data applications such as data mining and data publishing. How to protect people's privacy and prevent the leakage of sensitive information has become an urgent problem. For example, demographic data of a certain unit, illness records of h...

Full description

Saved in:
Bibliographic Details
Published in2023 International Conference on Mechatronics, IoT and Industrial Informatics (ICMIII) pp. 407 - 410
Main Authors Chen, Hongyun, Lv, Xingqin, Xu, Huanxiao, Mei, Xiangxiang, Zhu, Yangyan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2023
Subjects
Big Data applications
Data models
Data privacy
Dynamic datasets
Local modularity
Loss measurement
Mechatronics
Privacy
Privacy protection
Publishing
Online AccessGet full text

Cover

More Information
Summary:With the emergence and development of a large number of data applications such as data mining and data publishing. How to protect people's privacy and prevent the leakage of sensitive information has become an urgent problem. For example, demographic data of a certain unit, illness records of hospital patients, etc., are of great research value. Because these data often contain some private information of individuals, if the private information is leaked after the data is released, it will infringe on personal privacy. Anonymization technology can protect privacy information and ensure the authenticity of data released to the outside world, which is suitable for applications in many fields and has become a hot spot in the research field of privacy protection technology in recent years. However, most of the existing anonymous publishing technologies are based on static data sets, that is, assuming that the data sets are published "once" without any update. In other words, most privacy protection anonymous algorithms do not support the republication of data sets after insertion, deletion and modification. In reality, data sets are changing all the time. If the original static data set method is directly applied to the republishing process of dynamic data sets, it will lead to the leakage of a large amount of privacy information. Therefore, the republication of dynamic data sets faces more challenges.
DOI:10.1109/ICMIII58949.2023.00085