A PRIVACY PRESERVING CLUSTERING METHOD BASED ON FUZZY APPROACH AND RANDOM ROTATION PERTURBATION
M. Naga Lakshmi, K. Sandhya Rani · 2013
Individual privacy issues arise in these days when organizations using clustering as a data analysis tool. Private and sensitive data available in criminal, healthcare and financial records need to be preserved and also avoid the privacy leakage with the data mining system. In this paper, a privacy preserving clustering method is proposed for protecting the underlying sensitive attribute values when sharing the data for clustering over centralized data. The proposed method based on the concept of fuzzy logic and random rotation perturbation. This approach ensures secrecy of confidential numerical attributes without losing accuracy in results. The experiments demonstrate that the proposed method is effective and provides a feasible approach to balancing privacy and accuracy.