A multi-objective privacy preservation model for cloud security using hunter prey optimization algorithm

Maximizing the security of the cloud system is most important need of this world. Similarly, the data controllers are also increased stealing the sensitive and personal data from the cloud computing system. A repeated data violation occurs due to a large amount of outsourced and unsecured sensitive data. At present, numerous research works have been performed to secure the data in the cloud, but sometimes they do not succeed in securing the sensitive data. A Multi-Objective Privacy Preservation Model for Cloud Security utilizing Hunter Prey Optimization approach is proposed in this paper. Initially, the data is taken from 5 types of dataset like, concrete, Heart disease, Super Conductivity, Air Quality and wholesale customer datasets. The input data is given to the sanitization of data and restoration stage. In sanitization of data and restoration phase, SMA is utilized. After preventing the leakage in the data sanitization and restoration stage, the input data is applied to the key generation phase. Multi-objective functions such as the preservation of information ratio, the ratio of hiding, and the modification degree are performed at the key generation stage with the help of the hunter prey optimization algorithm to improve cloud data security. The proposed MOPP-CS-HPOA method is evaluated under some performances metrics, like modification degree, ratio of hiding, information preservation ratio, key sensitivity and computational time. Then the proposed MOPP-CS-HPOA method attains 35.69%, 38.504% and 31.805% higher information preservation ratio; 39.52%, 30.28% and 38.14% higher hiding ratio; analysed with MOPP-CS-JSSO, MOPP-CS-PS-BMFO and MOPP-CS-SVM-KNN-RF-NB-ANN methods.