| Title | Privacy-Preserving Correlated Data Publication with a Noise Adding Mechanism |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Sun, Mingjing, Zhao, Chengcheng, He, Jianping |
| Conference Name | 2020 IEEE 16th International Conference on Control Automation (ICCA) |
| Date Published | Oct. 2020 |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-9093-8 |
| Keywords | control theory, Correlation, Couplings, Data models, data privacy, Estimation, Human Behavior, privacy, Probabilistic logic, pubcrawl, resilience, Resiliency, Scalability |
| Abstract | The privacy issue in data publication is critical and has been extensively studied. However, most of the existing works assume the data to be published is independent, i.e., the correlation among data is neglected. The correlation is unavoidable in data publication, which universally manifests intrinsic correlations owing to social, behavioral, and genetic relationships. In this paper, we investigate the privacy concern of data publication where deterministic and probabilistic correlations are considered, respectively. Specifically, (ε,δ)-multi-dimensional data-privacy (MDDP) is proposed to quantify the correlated data privacy. It characterizes the disclosure probability of the published data being jointly estimated with the correlation under a given accuracy. Then, we explore the effects of deterministic correlations on privacy disclosure. For deterministic correlations, it is shown that the successful disclosure rate with correlations increases compared to the one without knowing the correlation. Meanwhile, a closed-form solution of the optimal disclosure probability and the strict bound of privacy disclosure gain are derived. Extensive simulations on a real dataset verify our analytical results. |
| URL | https://ieeexplore.ieee.org/document/9264434 |
| DOI | 10.1109/ICCA51439.2020.9264434 |
| Citation Key | sun_privacy-preserving_2020 |
Privacy-Preserving Correlated Data Publication with a Noise Adding Mechanism