Gradient-based label leakage attacks recover activity class labels from federated HAR updates with high accuracy, especially under sequential sampling, and standard local privacy defenses provide only partial protection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Label Leakage in Federated Inertial-based Human Activity Recognition
Gradient-based label leakage attacks recover activity class labels from federated HAR updates with high accuracy, especially under sequential sampling, and standard local privacy defenses provide only partial protection.