Coward detects backdoors in federated learning by injecting a collision-suppressed watermark on OOD data to invert the detection paradigm and limit OOD bias effects.
Robust aggregation for federated learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Federated aggregation strategies show distinct performance trade-offs in accuracy, loss, and efficiency depending on whether client data distributions are homogeneous or heterogeneous.
citing papers explorer
-
Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
Coward detects backdoors in federated learning by injecting a collision-suppressed watermark on OOD data to invert the detection paradigm and limit OOD bias effects.
-
A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
Federated aggregation strategies show distinct performance trade-offs in accuracy, loss, and efficiency depending on whether client data distributions are homogeneous or heterogeneous.