An Approach for Data Publishing with Sensitive Attribute Synthesis
Zhihui Wang, Yun Zhu, Xinyuan Mi · 2023
Data privacy preservation has been an important problem worthy of study. With the deepening of research, more targeted solutions for different requirements are proposed. Considering that in the most cases, only some of the data are sensitive, and there is no need to provide privacy preservation for non-sensitive data. This paper mainly addresses the problem of privacy preservation only for the sensitive attributes, and the non-sensitive data can be shared with the original values. A privacy preservation approach is presented in this paper, which synthesizes the values of sensitive data attributes and keeps the values of non-sensitive data attributes untouched during data publishing. The experimental results show that this approach can reduce the loss of information and thus improve the utility of published data.