DMPA is a collusive model poisoning attack for decentralized federated learning that negates and selectively replaces malicious model updates along the principal component of their correlation matrix.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences
DMPA is a collusive model poisoning attack for decentralized federated learning that negates and selectively replaces malicious model updates along the principal component of their correlation matrix.