A malicious federated-learning client can flip the global model's prediction on a target sample by crafting feature-unlearning requests on influence-function-selected samples.
Secure and efficient federated learning with provable performance guarantees via stochastic quantization,
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
unclear 1representative citing papers
citing papers explorer
-
FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks
A malicious federated-learning client can flip the global model's prediction on a target sample by crafting feature-unlearning requests on influence-function-selected samples.