FL-CLEANER filters Byzantine and backdoor model updates in federated learning under non-IID data by scoring clients with a conditional variational autoencoder on activation-map reconstruction errors and clustering the scores.
Emerging trends in federated learning: From model fusion to federated x learning
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
background 1representative citing papers
citing papers explorer
-
FL-CLEANER: byzantine and backdoor defense by CLustering Errors of Activation maps in Non-iid fedErated leaRning
FL-CLEANER filters Byzantine and backdoor model updates in federated learning under non-IID data by scoring clients with a conditional variational autoencoder on activation-map reconstruction errors and clustering the scores.