Daniel Scheliga

12 papers A* 1A 1Journal 8Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Lowering barriers to federated learning: collaboration management and provenance. J. Big Data Marius Schlegel, Daniel Scheliga, Kai-Uwe Sattler, Marco Seeland, Patrick Mäder
2026	J	`jnl`	Model utility and explainability in federated learning - A case study in healthcare using fundus oculi datasets. J. Biomed. Informatics Niklas Penzel, Daniel Scheliga, Hannes Oppermann, Patrick Mäder, Jens Haueisen, Joachim Denzler, Marco Seeland
2025	—	`—`	Federated learning with privacy modules to resist gradient inversion attacks. Daniel Scheliga
2025	J	`jnl`	Privacy preserving federated learning with convolutional variational bottlenecks. Cybersecur. Daniel Scheliga, Patrick Mäder, Marco Seeland
2024	—	`conf`	Collaboration Management for Federated Learning. ICDEW Marius Schlegel, Daniel Scheliga, Kai-Uwe Sattler, Marco Seeland, Patrick Mäder
2024	J	`jnl`	Feature-Based Dataset Fingerprinting for Clustered Federated Learning on Medical Image Data. Appl. Artif. Intell. Daniel Scheliga, Patrick Mäder, Marco Seeland
2023	A*	`conf`	Dropout Is NOT All You Need to Prevent Gradient Leakage. AAAI Daniel Scheliga, Patrick Maeder, Marco Seeland
2023	J	`jnl`	Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks. CoRR Daniel Scheliga, Patrick Mäder, Marco Seeland
2022	J	`jnl`	Combining Variational Modeling with Partial Gradient Perturbation to Prevent Deep Gradient Leakage. CoRR Daniel Scheliga, Patrick Mäder, Marco Seeland
2022	J	`jnl`	Dropout is NOT All You Need to Prevent Gradient Leakage. CoRR Daniel Scheliga, Patrick Mäder, Marco Seeland
2022	A	`conf`	PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage. WACV Daniel Scheliga, Patrick Mäder, Marco Seeland
2021	J	`jnl`	PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage. CoRR Daniel Scheliga, Patrick Mäder, Marco Seeland

2025 Best paper conf

Assessing the Effectiveness of the Tigress Obfuscator Against MOPSA and BinaryNinja.

CheckMATE

Nicolò Altamura, Enrico Bragastini, Marco Campion, Mila Dalla Preda

2026 Best paper preprint

ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage.

arXiv

Chang Liu, Noah Fleischmann, Nicolò Altamura, Edward Raff, James Holt, Kristopher Micinski