When Machine Learning Meets Privacy

Abstract

The newly emerged machine learning (e.g., deep learning) methods have become a strong driving force to revolutionize a wide range of industries, such as smart healthcare, financial technology, and surveillance systems. Meanwhile, privacy has emerged as a big concern in this machine learning-based artificial intelligence era. It is important to note that the problem of privacy preservation in the context of machine learning is quite different from that in traditional data privacy protection, as machine learning can act as both friend and foe. Currently, the work on the preservation of privacy and machine learning are still in an infancy stage, as most existing solutions only focus on privacy problems during the machine learning process. Therefore, a comprehensive study on the privacy preservation problems and machine learning is required. This article surveys the state of the art in privacy issues and solutions for machine learning. The survey covers three categories of interactions between privacy and machine learning: (i) private machine learning, (ii) machine learning-aided privacy protection, and (iii) machine learning-based privacy attack and corresponding protection schemes. The current research progress in each category is reviewed and the key challenges are identified. Finally, based on our in-depth analysis of the area of privacy and machine learning, we point out future research directions in this field.

Designing ECG monitoring healthcare system with federated transfer learning and explainable AI

“…As discussed earlier that it may cause privacy concerns among users and data owners. Thereafter, traditional centralized healthcare applications find limited applicability due to privacy concerns [39,40,41]. To address the privacy issues in machine learning, researchers have been working on Federated learning (FL) and Transfer learning (TF).…”

A Critical Overview of Privacy in Machine Learning

“…NB: This article is not meant to present a comprehensive survey of literature in the field, nor an exhaustive list of all threat models and attacks of privacy in machine learning; interested readers may refer to existing surveys, e.g., [1].…”

Toward Learning Trustworthily from Data Combining Privacy, Fairness, and Explainability: An Application to Face Recognition

“…For what concerns the methods for making ML models privacy-aware/compliant, they can be divided into anonymization techniques, perturbation techniques, and distributed protocols [28,87,88]. The anonymization techniques try to maintain the privacy of the data subjects by obscuring personally identifying information within a dataset while preserving data utility.…”