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.
Ma- chine learning with adversaries: Byzantine tolerant gradient descent
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
A representation-level divergence metric is introduced to detect atypical clients in federated learning by quantifying changes in activation-induced input-space partitions on a shared probe set.
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.
-
Detecting Atypical Clients in Federated Learning via Representation-Level Divergence
A representation-level divergence metric is introduced to detect atypical clients in federated learning by quantifying changes in activation-induced input-space partitions on a shared probe set.