Daniel Scheliga

According to our database, Daniel Scheliga authored at least 4 papers between 2022 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2023

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks.

Daniel Scheliga, Patrick Mäder, Marco Seeland

CoRR, 2023

Dropout Is NOT All You Need to Prevent Gradient Leakage.

Daniel Scheliga, Patrick Maeder, Marco Seeland

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Combining Variational Modeling with Partial Gradient Perturbation to Prevent Deep Gradient Leakage.

Daniel Scheliga, Patrick Mäder, Marco Seeland

CoRR, 2022

PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage.

Daniel Scheliga, Patrick Mäder, Marco Seeland

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022