An FL scheme combining client grouping, gradient splitting, performance-based malicious detection, and threshold encryption aims to resist gradient inversion and poisoning attacks, claiming over 95% malicious-client localization accuracy.
A survey on federated learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SMTFL: Secure Model Training to Untrusted Participants in Federated Learning
An FL scheme combining client grouping, gradient splitting, performance-based malicious detection, and threshold encryption aims to resist gradient inversion and poisoning attacks, claiming over 95% malicious-client localization accuracy.