Privacy preserving DBSCAN clustering algorithm for vertically partitioned data in distributed systems

Abstract

We suggested the modification of DBSCAN clustering algorithm for vertically partitioned big data. This modification provides privacy of the information which is transmitted via telecommunication channels between nodes of big data storage. This modification is founded on organization of secure channel which is based on homomorfic and asymmetric encryption. The first one is used for hiding the information and the second one is used for creation the encryption channel. Suggested privacy preserving DBSCAN clustering algorithm provides data confidentiality at all steps of DBSCAN algorithm.