FAUN recovers poisoned federated learning models via adversarial updates on a proxy dataset, matching retraining performance with far fewer rounds and near-zero attack success.
Our method FAUN exploits the server’s ability to store historical client updates and to utilize a small proxy dataset for adversarial optimiza- tion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery
FAUN recovers poisoned federated learning models via adversarial updates on a proxy dataset, matching retraining performance with far fewer rounds and near-zero attack success.