A server that keeps one example per class can detect and drop malicious federated-learning clients by measuring how separated their learned embeddings are, via the norm of a Gram matrix.
Baffle: Backdoor detection via feedback-based federated learning
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
-
FedGraM: Defending Against Untargeted Attacks in Federated Learning via Embedding Gram Matrix
A server that keeps one example per class can detect and drop malicious federated-learning clients by measuring how separated their learned embeddings are, via the norm of a Gram matrix.