A defense mechanism against label inference attacks in Vertical Federated Learning
Neurocomputing · 2025-04 · 624 · 129476
DOI: 10.1016/j.neucom.2025.129476 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurocomputing, 2025-04. Verfasst von Marco Arazzi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministero dell'Università e della Ricerca.
Abstract (Originalsprache)
Vertical Federated Learning (VFL) is a category of Federated Learning in which models are trained collaboratively among parties with vertically partitioned data. Typically, in a VFL scenario, the labels of the samples are kept private from all the parties except for the aggregating server, that is the label owner. Nevertheless, recent works discovered that by exploiting gradient information returned by the server to bottom models, with the knowledge of only a small set of auxiliary labels on a very limited subset of training data points, an adversary can infer the private labels. These attacks are known as label inference attacks in VFL. In our work, we propose a novel framework called KDk, that combines Knowledge Distillation and k-anonymity to provide a defense mechanism against potential label inference attacks in a VFL scenario. Through an exhaustive experimental campaign we demonstrate that by applying our approach, the performance of the analyzed label inference attacks decreases consistently, even by more than 60%, maintaining the accuracy of the whole VFL almost unaltered.
Förderung
- Ministero dell'Università e della Ricerca
Zitieren
APA
Arazzi, M., Nicolazzo, S., & Nocera, A. (2025). A defense mechanism against label inference attacks in Vertical Federated Learning. Neurocomputing, 624, 129476. https://doi.org/10.1016/j.neucom.2025.129476
Vancouver
Arazzi M, Nicolazzo S, Nocera A. A defense mechanism against label inference attacks in Vertical Federated Learning. Neurocomputing. 2025;624:129476. doi:10.1016/j.neucom.2025.129476
BibTeX
@article{Arazzi2025,
author = {Arazzi, Marco and Nicolazzo, Serena and Nocera, Antonino},
title = {A defense mechanism against label inference attacks in Vertical Federated Learning},
journal = {Neurocomputing},
year = {2025},
volume = {624},
pages = {129476},
doi = {10.1016/j.neucom.2025.129476}
}
EUVIMED