Secure model for clustering distributed data

Data of similar nature are disseminated across organizations and needs to be analyzed to discover patterns and obtain relevant conclusions. While mining distributed data, disclosure of the sensitive information is a limitation that needs to be handled. This paper focuses on the construction of one such privacy preserving clustering approach that clusters, scattered data using the k-means strategy securely. The proposed approach provides maximum security of the sensitive data while modeling and also generates accurate results in comparison to the past related approaches.