An Ontology based Personalized Privacy Preservation

Abstract

Various organizations share sensitive personal data for data analysis. Therefore, sensitive information must be protected. For this purpose, privacy preservation has become a major issue along with the data disclosure in data publishing. Hence, an individual’s sensitive data must be indistinguishable after the data publishing. Data anonymization techniques perform various operations on data before it’s shared publicly. Also, data must be available for accurate data analysis when data is released. Therefore, differential privacy method which adds noise to query results is used. The purpose of data anonymization is to ensure that data cannot be misused even if data are stolen and to enhance the privacy of individuals. In this paper, an ontology-based approach is proposed to support privacy-preservation methods by integrating data anonymization techniques in order to develop a generic anonymization model. The proposed personalized privacy approach also considers individuals’ different privacy concerns and includes privacy preserving algorithms’ concepts.