A Systematic Literature Review On Privacy Of Deep Learning Systems

TL;DR

This paper systematically reviews privacy concerns and security attacks in deep learning systems, emphasizing the importance of privacy-preserving solutions and future research directions in the field.

Contribution

It provides a comprehensive overview of security attacks and privacy-preserving methods in deep learning, highlighting gaps and future research opportunities.

Findings

Deep learning models are vulnerable to various security attacks.

Multiple privacy-preserving solutions are identified and evaluated.

The review suggests future research directions in privacy and deep learning.

Abstract

The last decade has seen a rise of Deep Learning with its applications ranging across diverse domains. But usually, the datasets used to drive these systems contain data which is highly confidential and sensitive. Though, Deep Learning models can be stolen, or reverse engineered, confidential training data can be inferred, and other privacy and security concerns have been identified. Therefore, these systems are highly prone to security attacks. This study highlights academic research that highlights the several types of security attacks and provides a comprehensive overview of the most widely used privacy-preserving solutions. This relevant systematic evaluation also illuminates potential future possibilities for study, instruction, and usage in the fields of privacy and deep learning.