FedBAP defends federated learning against backdoor attacks by reverse-engineering trigger-like patterns and training clients to ignore them, reporting attack success rates below 3% in experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
FedBAP defends federated learning against backdoor attacks by reverse-engineering trigger-like patterns and training clients to ignore them, reporting attack success rates below 3% in experiments.