Research on K-Means Clustering Algorithm Over Encrypted Data

Aiming at the privacy-preserving problem in data mining process, this paper proposes an improved K-Means algorithm over encrypted data, called HK-means++ that uses the idea of homomorphic encryption to solve the encrypted data multiplication problems, distance calculation problems and the comparison problems. Then apply these security protocols to the improved clustering algorithm framework. To prevent the leakage of privacy while calculating the distance between the sample points and the center points, it prevents the attacker from inferring the cluster grouping of the user by hiding the cluster center. To some extent, it would reduce the risk of leakage of private data in the cluster mining process. It is well known that the traditional K-Means algorithm is too dependent on the initial value. In this paper, we focus on solving the problem to reduce the number of iterations, and improve the clustering efficiency. The experimental results demonstrate that our proposed, HK-Means algorithm has good clustering performance and the running time is also reduced.