Daniel Scheliga

According to our database, Daniel Scheliga authored at least 9 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Lowering barriers to federated learning: collaboration management and provenance.

Marius Schlegel, Daniel Scheliga, Kai-Uwe Sattler, Marco Seeland, Patrick Mäder

J. Big Data, December, 2026

Model utility and explainability in federated learning - A case study in healthcare using fundus oculi datasets.

Niklas Penzel, Daniel Scheliga, Hannes Oppermann, Patrick Mäder, Jens Haueisen, Joachim Denzler, Marco Seeland

J. Biomed. Informatics, 2026

2025

Privacy preserving federated learning with convolutional variational bottlenecks.

Daniel Scheliga, Patrick Mäder, Marco Seeland

Cybersecur., December, 2025

Federated learning with privacy modules to resist gradient inversion attacks.

Daniel Scheliga

PhD thesis, 2025

2024

Feature-Based Dataset Fingerprinting for Clustered Federated Learning on Medical Image Data.

Daniel Scheliga, Patrick Mäder, Marco Seeland

Appl. Artif. Intell., December, 2024

Collaboration Management for Federated Learning.

Marius Schlegel, Daniel Scheliga, Kai-Uwe Sattler, Marco Seeland, Patrick Mäder

Proceedings of the 40th International Conference on Data Engineering, ICDE 2024, 2024

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