Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMs
ACM Transactions on Intelligent Systems and Technology · 28.02.2027 · 18 (1) · 1-70
DOI: 10.1145/3832316 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 29.09.2026. Verfasst von Francisco Aguilera-Martinez und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 278 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Machine learning models should not reveal particular information that is not otherwise accessible. Differential Privacy (DP) provides a formal framework to mitigate privacy risks by ensuring that the inclusion or exclusion of any single data point does not significantly alter the output of an algorithm, thus limiting the exposure of private information. This survey reviews the foundational definitions of DP and traces their evolution through key theoretical and applied contributions. It then provides an in-depth examination of how DP has been integrated into machine learning models, analyzing existing proposals and methods to preserve privacy when training ML models. Finally, it describes how DP-based ML techniques can be evaluated in practice. By offering a comprehensive overview of DP in machine learning, this work aims to contribute to the ongoing development of secure and responsible AI systems.
Zitieren
APA
Aguilera-Martinez, F., & Berzal, F. (2027). Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMs. ACM Transactions on Intelligent Systems and Technology, 18(1), 1-70. https://doi.org/10.1145/3832316
Vancouver
Aguilera-Martinez F, Berzal F. Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMs. ACM Transactions on Intelligent Systems and Technology. 2027;18(1):1-70. doi:10.1145/3832316
BibTeX
@article{AguileraMartinez2027,
author = {Aguilera-Martinez, Francisco and Berzal, Fernando},
title = {Differential Privacy in Machine Learning: A Survey from Symbolic AI to LLMs},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2027},
volume = {18},
number = {1},
pages = {1--70},
doi = {10.1145/3832316}
}
EUVIMED