Attackers Are Not the Same! Unveiling the Impact of Feature Distribution on Label Inference Attacks

As a distributed machine learning paradigm, vertical federated learning enables multiple passive parties with distinct features and an active party with labels to train a model collaboratively. Although it has been widely applied for its ability to protect privacy to some extent, this paradigm still...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on information forensics and security 2024-11, p.1-1
Hauptverfasser:	Liu, Yige, Wang, Che, Lou, Yiwei, Cao, Yongzhi, Wang, Hanpin
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Computational modeling Data models defense differential privacy feature distribution Federated learning label inference attack Noise Perturbation methods Predictive models Privacy Threat modeling Vectors vertical federated learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!