An interpolation approximation plus layer-weighted loss enables stronger data reconstruction attacks on FedAvg federated learning, with experiments showing gains on image data over prior methods.
On Bayesian methods for seeking the extremum,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Approximate and Weighted Data Reconstruction Attack in Federated Learning
An interpolation approximation plus layer-weighted loss enables stronger data reconstruction attacks on FedAvg federated learning, with experiments showing gains on image data over prior methods.