The Limitations of Differential Privacy in Synthetic Data

Privacy takes a different view by measuring the maximum influence that any one individual could have on a particular outcome. For example, whether you participate in a study or not, the results of the study should be more or less the same. Privacy only concerned itself about the probability functions, wac was the probability of certain events. However, the sample of space itself could also lead some information, depending on how it is constructed. And therefore, if you want to have private, syntheticdata, you need to think how you construct the sample space as well.