User data privacy preservation and correct balance of privacy and utility

Abstract

Privacy and utility are trade-off considerations, where one factor's performance must be sacrificed to attain the other. If privacy is obtained without disclosing the data, efficient utility cannot be obtained; hence, the original dataset tends to be released without privacy. As a result, it is critical to maintain the balance between dataset privacy and utility. We present a new privacy utility approach in this research, where privacy is maintained by lightweight elliptical curve cryptography (ECC) and utility is maintained via ant colony optimisation (ACO) clustering. The datasets are initially grouped using ACO, and subsequently the privacy of the clustered datasets is preserved using ECC. The suggested technique has been tested on medical datasets and compared to current methods using a variety of performance metrics.