Differential Privacy through Knowledge Refinement
Jordi Soria-Comas, Josep Domingo‐Ferrer · 2012
We introduce a novel mechanism to attain differential privacy. Contrary to the common mechanism based on the addition of a noise whose magnitude is proportional to the sensitivity of the query function, our proposal is based on the refinement of the user's prior knowledge about the response. We show that our mechanism has several advantages over noise addition: it does not require complex computations, and thus it can be easily automated, it lets the user exploit her prior knowledge about the response to achieve better data quality, and it is independent of the sensitivity of the query function (although this can be a disadvantage if the sensitivity is small). We also show some compounding properties of our mechanism for the case of multiple queries.