Privacy protection scheme of DBSCAN clustering based on homomorphic encryption

In order to reduce the risk of data privacy leakage in the process of outsourced clustering, a privacy protection scheme of DBSCAN clustering based on homomorphic encryption was proposed.In order to encrypt the float data in the actual scene, three data preprocessing methods for different data accuracy were given, and a policy for choosing a proper data preprocessing method based on data characteristics, accuracy and computational cost was also proposed.For the ciphertext comparison operation that was not supported by homomorphic encryption, a protocol between the client and the cloud server was designed to realize the function of ciphertext comparison.Theoretical analysis and experimental results show that the proposed scheme can ensure the security of data privacy, and has a higher clustering accuracy rate and lower time overhead.