Data Privacy-Preservation: A Method of Machine Learning

Abstract

The privacy-preservation field in cyber security tends to affiliate with the protection measure related to the use of data and its sharing via third parties for activities such as data analysis. The paper's main objective for this research article will be to use machine learning models that tend to aid as a privacy-preservation technique (PPT). The augmentation of machine learning as a technique for privacy preservation has been able to address the challenges facing the current field of cyber security concerning data protection and security. The paper summarizes the methods such as "federated learning" to address the current issue in the network security field relating to data protection. The rise of augmentation of machine learning in privacy preservation is due to the development of cloud-based applications that are usually prone to data protection issues. Thus, the result of machine learning was necessary to counteract data insecurity. However, the use of machine learning in privacy preservation has remained proficient; there still needs to be a literature gap between the theory and the application of machine learning.