Privacy preserving framework using Gaussian mutation based firebug optimization in cloud computing

In recent years, the data exchange among the service providers and users has been increased tremendously. Various organizations like banking sectors, health as well as government associations collect and process the data regarding an individual for their benefcial purpose. However, data confdentiality and data privacy are still considered as signifcant challenges while sharing sensitive data. The cloud stor-
age servers based on unencrypted data are susceptible to both external and internal attacks established by strangers or untrustworthy cloud service providers. Since the medical data are sensitive, the risk based on privacy enhances at the moment of subcontracting entity medical records to the cloud. The signifcant intention of the proposed approach involves securing and preserving sensitive healthcare data. Here, data hiding and data restoration operations are considered as two signifcant opera- tions of the proposed framework. Initially, an optimal key is generated in the data hiding operation. This paper proposes a Gaussian mutation-based frebug optimiza-tion (GM-FBO) algorithm for the generation of an optimal key. The experiments are conducted using three diferent healthcare datasets, namely HPD, Medical MIMIC- III, and MHEALTH. The efciency of the proposed model is compared with difer-ent state-of-the-art techniques to determine the efciency of the system.