TOFD defends split federated learning against five classes of poisoning attacks by combining class-wise target inference, sample purification, and adversarial feature decoupling.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning
TOFD defends split federated learning against five classes of poisoning attacks by combining class-wise target inference, sample purification, and adversarial feature decoupling.