Search Results for author:
Found 4 papers, 2 papers with code
Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks
To preserve the privacy preserving effect of PRECODE, our analysis reveals that variational modeling must be placed early in the network.
Dropout is NOT All You Need to Prevent Gradient Leakage
We find that state of the art attacks are not able to reconstruct the client data due to the stochasticity induced by dropout during model training.
Combining Variational Modeling with Partial Gradient Perturbation to Prevent Deep Gradient Leakage
In result, we show that our approach requires less gradient perturbation to effectively preserve privacy without harming model performance.
PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage
We propose a simple yet effective realization of PRECODE using variational modeling.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
