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.
Rflbat: A robust fed- erated learning algorithm against backdoor attack
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CR 2verdicts
CONDITIONAL 2roles
baseline 1polarities
baseline 1representative citing papers
SecureAFL secures asynchronous federated learning against poisoning attacks by detecting anomalous updates, estimating missing client contributions, and using Byzantine-robust aggregation.
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.
-
SecureAFL: Secure Asynchronous Federated Learning
SecureAFL secures asynchronous federated learning against poisoning attacks by detecting anomalous updates, estimating missing client contributions, and using Byzantine-robust aggregation.