A shadow-model-based defense adds sample-specific noise to medical images in federated learning, weakening gradient inversion attacks while keeping model accuracy near baseline.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Shadow defense against gradient inversion attack in federated learning
A shadow-model-based defense adds sample-specific noise to medical images in federated learning, weakening gradient inversion attacks while keeping model accuracy near baseline.