I am a Ph.D. student at CISPA Helmholtz Center for Information Security, supervised by Jilles Vreeken. I am broadly interested in robust and explainable machine learning for large-scale real-world applications. In my Ph.D, I intend to develop new approaches that are at the same time descriptive and predictive. That is the models not only offer predictive capabilities but also facilitate practitioners to gain deeper insights into the problems they are addressing.
I obtained my Bachelor's and Master's degrees in Computer Science from Saarland University. Before joining CISPA, I was a research assistant in the goup of Bernt Schiele at the Max-Planck-Institut for Informatics, supervised by David Stutz . My research focused on adversarial and out-of-distribution robustness of Quantized Neural Networks. I also worked on the influence of Batch Normalization on the vulnerability and generalization capabilities of neural networks.
2026 | |
When Flatness Does (Not) Guarantee Adversarial Robustness. In: Proceedings of the International Conference on Representation Learning (ICLR), OpenReview, 2026. (28.2% acceptance rate) |
|
Learning and Naming Subgroups with Exceptional Survival Characteristics. Technical Report 2602.22179, arXiv, 2026. |
|
2025 | |
Neural Rule Lists: Learning Discretizations, Rules, and Order in One Go. In: Proceedings of Neural Information Processing Systems (NeurIPS), PMRL, 2025. (24.5% acceptance rate) |
|
Can LLMs Subtract Numbers?. In: Proceedings of the EMNLP Workshop on Mathematical Natural Language Processing (MathNLP), 2025. |
|
Hidden in Plain Sight - Class Competition Focuses Attribution Maps. Technical Report 2503.07346, arXiv, 2025. |
|
2024 | |
Finding Interpretable Class-Specific Patterns through Efficient Neural Search. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp 9062-9070, AAAI, 2024. (23.8% acceptance rate) |
|
Learning Exceptional Subgroups by End-to-End Maximizing KL-divergence. In: Proceedings of the International Conference on Machine Learning (ICML), PMLR, 2024. (spotlight, 3.5% acceptance rate; 27.5% overall) |
|
The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective. Technical Report 2405.16918, arXiv, 2024. |
|
2022 | |
On Fragile Features and Batch Normalization in Adversarial Training. Technical Report 2204.12393, arXiv, 2022. |
|