2 papers
cs.CR2026
VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Masking
Juntao Tan, Lan Zhang, Zhonghao Hu +3
Though vertical federated learning (VFL) is generally considered to be privacy-preserving, recent studies have shown that VFL system is vulnerable to label inference attacks origin…
cs.CR2026
VTarbel: Targeted Label Attack with Minimal Knowledge on Detector-enhanced Vertical Federated Learning
Juntao Tan, Anran Li, Quanchao Liu +2
Vertical federated learning (VFL) enables multiple parties with disjoint features to collaboratively train models without sharing raw data. While privacy vulnerabilities of VFL are…