Differentially Private Response Mechanisms on Categorical Data
This work addresses privacy-preserving data analysis for sensitive datasets, offering theoretical improvements in error bounds for differential privacy mechanisms, but it appears incremental as it builds on existing frameworks without introducing a new paradigm.
The paper tackles the problem of designing differentially private mechanisms for categorical data by deriving sufficient sets that provide necessary and sufficient conditions for differential privacy, resulting in a tight lower bound on maximal expected error and a characterization of the optimal mechanism that minimizes this error.
We study mechanisms for differential privacy on finite datasets. By deriving \emph{sufficient sets} for differential privacy we obtain necessary and sufficient conditions for differential privacy, a tight lower bound on the maximal expected error of a discrete mechanism and a characterisation of the optimal mechanism which minimises the maximal expected error within the class of mechanisms considered.