State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey

TL;DR

This survey reviews current privacy-preserving techniques in machine learning, analyzing threat models, privacy risks, and countermeasures like cryptography and differential privacy to protect sensitive training data across various applications.

Contribution

It provides a comprehensive overview of privacy-preserving strategies in ML, highlighting recent advances, challenges, and the balance between privacy and utility in different settings.

Findings

Cryptographic methods enhance data confidentiality.

Differential Privacy reduces privacy leakage.

Trade-offs exist between privacy and model accuracy.

Abstract

This paper examines the evolving landscape of machine learning (ML) and its profound impact across various sectors, with a special focus on the emerging field of Privacy-preserving Machine Learning (PPML). As ML applications become increasingly integral to industries like telecommunications, financial technology, and surveillance, they raise significant privacy concerns, necessitating the development of PPML strategies. The paper highlights the unique challenges in safeguarding privacy within ML frameworks, which stem from the diverse capabilities of potential adversaries, including their ability to infer sensitive information from model outputs or training data. We delve into the spectrum of threat models that characterize adversarial intentions, ranging from membership and attribute inference to data reconstruction. The paper emphasizes the importance of maintaining the confidentiality and integrity of training data, outlining current research efforts that focus on refining training data to minimize privacy-sensitive information and enhancing data processing techniques to uphold privacy. Through a comprehensive analysis of privacy leakage risks and countermeasures in both centralized and collaborative learning settings, this paper aims to provide a thorough understanding of effective strategies for protecting ML training data against privacy intrusions. It explores the balance between data privacy and model utility, shedding light on privacy-preserving techniques that leverage cryptographic methods, Differential Privacy, and Trusted Execution Environments. The discussion extends to the application of these techniques in sensitive domains, underscoring the critical role of PPML in ensuring the privacy and security of ML systems.