| Precode-a generic model extension to prevent deep gradient leakage D Scheliga, P Mäder, M Seeland Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2022 | 55 | 2022 |
| Dropout is not all you need to prevent gradient leakage D Scheliga, P Mäder, M Seeland Proceedings of the AAAI Conference on Artificial Intelligence 37 (8), 9733-9741, 2023 | 13 | 2023 |
| Privacy preserving federated learning with convolutional variational bottlenecks D Scheliga, P Mäder, M Seeland arXiv preprint arXiv:2309.04515, 2023 | 5 | 2023 |
| Combining Variational Modeling with Partial Gradient Perturbation to Prevent Deep Gradient Leakage D Scheliga, P Mäder, M Seeland arXiv preprint arXiv:2208.04767, 2022 | 3 | 2022 |
| Feature-based Dataset Fingerprinting for Clustered Federated Learning on Medical Image Data D Scheliga, P Mäder, M Seeland Applied Artificial Intelligence 38 (1), 2394756, 2024 | 1 | 2024 |
| Collaboration Management for Federated Learning M Schlegel, D Scheliga, KU Sattler, M Seeland, P Mäder 2024 IEEE 40th International Conference on Data Engineering Workshops (ICDEW …, 2024 | | 2024 |
| Model-based data generation for the evaluation of functional reliability and resilience of distributed machine learning systems against abnormal cases R Altschaffel Deutsche Nationalbibliothek, 2023 | | 2023 |
| PRECODE-A Generic Model Extension to Prevent Deep Gradient Leakage–Supplementary Material– D Scheliga, P Mäder, M Seeland | | |
