PROJECT TITLE :
More Hybrid and Secure Protection of Statistical Data Sets
Totally different strategies and paradigms to shield data sets containing sensitive statistical info are proposed and studied. The thought is to publish a perturbed version of the data set that doesn't leak confidential data, however that still allows users to get meaningful statistical values regarding the original information. The two main paradigms for information set protection are the classical one and the synthetic one. Recently, the possibility of mixing the two paradigms, leading to a hybrid paradigm, has been thought of. In this work, we 1st analyze the protection of some synthetic and (partially) hybrid methods that have been proposed within the last years, and we conclude that they suffer from a high interval disclosure risk. We have a tendency to then propose the first fully hybrid SDC strategies; unfortunately, they additionally suffer from a quite high interval disclosure risk. To mitigate this, we propose a postprocessing technique that can be applied to any data set protected with a artificial technique, with the goal of reducing its interval disclosure risk. We tend to describe through the paper a set of experiments performed on reference knowledge sets that support our claims.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here