EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey

Lea Demelius, Roman Kern, Andreas Trügler

ACM Computing Surveys · 30.06.2025 · 57 (6) · 1-28

DOI: 10.1145/3712000 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.02.2025. Verfasst von Lea Demelius und 2 weiteren Autor:innen. Die Arbeit wurde bisher 62-mal zitiert (Crossref) und nennt 151 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AI for Green programme, Republic of Austria, Ministry of Climate Action, Austrian Federal Ministry (BMK and BMDW), the Austrian Research Promotion Agency (FFG), the province of Styria.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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: emerging application domains, differentially private generative models, auditing and evaluation methods for private models, protection against a broad range of threats and attacks, and improvements of privacy-utility tradeoffs.

Förderung

  • AI for Green programme
  • Republic of Austria, Ministry of Climate Action
  • Austrian Federal Ministry (BMK and BMDW), the Austrian Research Promotion Agency (FFG), the province of Styria

Zitieren

APA

Demelius, L., Kern, R., & Trügler, A. (2025). Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey. ACM Computing Surveys, 57(6), 1-28. https://doi.org/10.1145/3712000

Vancouver

Demelius L, Kern R, Trügler A. Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey. ACM Computing Surveys. 2025;57(6):1-28. doi:10.1145/3712000

BibTeX
@article{Demelius2025,
  author = {Demelius, Lea and Kern, Roman and Trügler, Andreas},
  title = {Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey},
  journal = {ACM Computing Surveys},
  year = {2025},
  volume = {57},
  number = {6},
  pages = {1--28},
  doi = {10.1145/3712000}
}
Kostenlos starten →