Parameter determination of ONN (Ordered Neural Networks)

Abstract

The need for data privacy motivates the development of new methods that allow to protect data minimizing the disclosure risk without losing information. In this paper, we propose a new protection method for numerical data called Ordered Neural Networks (ONN) method. ONN presents a new way to protect data based on the use of Artificial Neural Networks (ANN). ONN combines the use of ANN with a new strategy for preprocessing data consisting in the vectorization, sorting and partitioning of all the values in the attributes to be protected in the data set. We also present an statistical analysis that allows to understand the most important parameters affecting the quality of our method, and we show that it is possible to find a good configuration for these parameters. Finally, we compare our method to the best methods presented in the literature, using data provided by the US Census Bureau. Our experiments show that ONN outperforms the previous methods proposed in the literature, proving that the use of ANNs in these situations is convenient to protect the data efficiently without losing the statistical properties of the set.