Benign clients' training hyperparameters act as a backdoor-defense lever: choosing higher learning rates, more local epochs, and smaller batch sizes substantially reduces backdoor attack success in horizontal federated learning.
Zico Kolter, and Ameet Talwalkar
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
On Hyperparameters and Backdoor-Resistance in Horizontal Federated Learning
Benign clients' training hyperparameters act as a backdoor-defense lever: choosing higher learning rates, more local epochs, and smaller batch sizes substantially reduces backdoor attack success in horizontal federated learning.