ODD Visualizer: Scalable open data de-identification visualizer

Due to the significant values it can derive, large-scaled open data analysis (or big data analysis) attracts lots of attentions from various domains researchers and experts. However, the progresses of data releasing for open usages are still slow in the latest decade. Only about 10% amount of datasets owned by worldwide governments have been released, and the main reason of that is due to concern for "privacy preserving'. According to previous real case studies, even though the personally identifiable information have been de-identified, sensitive personal information still could be uncovered by heterogeneous or crossdomain data joining operation. This kind of privacy re-identification are usually too complicated or obscure to be realized by data owner, not to mention that this problem will be more severe as the scale of data goes large. To our best knowledge so far, none of existent research work leverages data visualization approach to provide direct and clear manner detecting information re-identification problem. In this project, we aim to propose a method for scalable open data de-identification visualization consisting of: 1) platform for scalable storing and computation for de-identification measuring and 2) novel data visualization technique depicting distribution of de-identification robustness in a global view. It was demonstrated that our work not only provides efficient estimation and visualization for data de-identification but also a useful guideline helping users determine which parts of data should be released or not.