Saved in:
Bibliographic Details
Main Authors: Demelius, Lea, Kern, Roman, Trügler, Andreas
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.16398
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912621273284608
author Demelius, Lea
Kern, Roman
Trügler, Andreas
author_facet Demelius, Lea
Kern, Roman
Trügler, Andreas
contents Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state-of-the-art of differentially private centralized deep learning, thorough analyses of recent advances and open problems, as well as a discussion of potential future developments in the field. Based on a systematic literature review, the following topics are addressed: auditing and evaluation methods for private models, improvements of privacy-utility trade-offs, protection against a broad range of threats and attacks, differentially private generative models, and emerging application domains.
format Preprint
id arxiv_https___arxiv_org_abs_2309_16398
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
Demelius, Lea
Kern, Roman
Trügler, Andreas
Machine Learning
Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees. This survey provides an overview of the state-of-the-art of differentially private centralized deep learning, thorough analyses of recent advances and open problems, as well as a discussion of potential future developments in the field. Based on a systematic literature review, the following topics are addressed: auditing and evaluation methods for private models, improvements of privacy-utility trade-offs, protection against a broad range of threats and attacks, differentially private generative models, and emerging application domains.
title Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
topic Machine Learning
url https://arxiv.org/abs/2309.16398