Non-cryptographic privacy preserving machine learning methods: a review

Abstract

In recent years, the use of Machine Learning (ML) techniques to exploit data and produce predictive models has become widespread in decision-making and problem-solving across various fields, including healthcare, energy, retail, transportation, and many more. Generally, a well-performing ML model requires large volumes of training data. However, collecting data and using it to predict behavior poses significant challenges to the privacy of individuals and organizations, such as data breaches, loss of privacy, and corresponding financial damage. Therefore, well-designed privacy-preserving ML (PPML) methods are significantly required for many emerging applications to mitigate these problems. This paper provides a comprehensive review of non-cryptographic privacy-preserving ML along with selected methods, such as differential privacy and federated learning. This paper aims to provide a roadmap for future research directions in the PPML field.