Anonymization ToolBox

In an effort to promote our research in the area of privacy preserving data analysis, at UT Dallas Data Security and Privacy Lab, we complied our implementation of various anonymization methods into a toolbox for public use by researchers. The algorithms can either be applied directly to a dataset or can be used as library functions inside other applications.

The toolbox currently contains 6 different anonymization methods over 3 different privacy definitions:

  • Datafly
  • Mondrian Multidimensional k-Anonymity
  • Incognito
  • Incognito with l-diversity
  • Incognito with t-closeness
  • Anatomy

Together with the anonymization toolbox, we also release the source code of our recent study on classifying anonymized data. In this study, we proposed methods for building distance-based classification models over anonymized data. More specifically, investigated methods include instance-based classifiers and support vector machines.

This work was partially supported by National Institutes of Health Grant 1R01LM009989, National Science Foundation Grant Career-0845803 and Air Force Office of Scientific Research MURI Grant FA9550-08-1-0265.

UTD Anonymization ToolBox is open source software issued under the GNU General Public License.