Nils Philipp Walter

I am a first year 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.

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.




  1. arXiv
    The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspective
    Nils Philipp Walter, Linara Adilova, Jilles Vreeken, and Michael Kamp
    arXiv preprint arXiv:2405.16918, 2024
  2. ICML
    Learning Exceptional Subgroups by End-to-End Maximizing KL-divergence
    Sascha Xu, Nils Philipp Walter, Janis Kalofolias, and Jilles Vreeken
    In Proceedings of the International Conference on Machine Learning (ICML), 2024
  3. AAAI
    Finding Interpretable Class-Specific Patterns through Efficient Neural Search
    Nils Philipp Walter, Jonas Fischer, and Jilles Vreeken
    In Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence, 2024


  1. CVPR
    On Fragile Features and Batch Normalization in Adversarial Training
    Nils Philipp Walter, David Stutz, and Bernt Schiele
    arXiv preprint arXiv:2204.12393, 2022