Privacy in Deep Learning: A Survey

TL;DR

This survey reviews privacy challenges in deep learning, including data leaks and inference attacks, and discusses existing mitigation techniques while highlighting gaps in test-time inference privacy and future research directions.

Contribution

It provides a comprehensive overview of privacy issues in deep learning and identifies a gap in test-time inference privacy research, proposing future directions.

Findings

Deep learning raises significant privacy concerns due to data sensitivity.

Various techniques exist to mitigate privacy risks, but gaps remain.

Test-time inference privacy is an underexplored area with future research potential.

Abstract

The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large datasets and high computational power are the main contributors to these advances. The datasets are usually crowdsourced and may contain sensitive information. This poses serious privacy concerns as this data can be misused or leaked through various vulnerabilities. Even if the cloud provider and the communication link is trusted, there are still threats of inference attacks where an attacker could speculate properties of the data used for training, or find the underlying model architecture and parameters. In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues. We also show that there is a gap in the literature regarding test-time inference privacy, and propose possible future research directions.