I am an adjunct professor (Privatdozent in German) at the Technical University of Munich (TUM), where I lead the Privacy-Preserving and Trustworthy Artificial Intelligence research group at the Institute for Artificial Intelligence in Medicine. I also lead the Reliable AI research group at Helmholtz Munich.
I completed my post-doc in Artificial Intelligence with Professor Daniel Rueckert at the Department of Computing at Imperial College London, where I remain a visiting researcher.
Before dedicating myself to full-time AI research, I obtained my specialist diagnostic radiologist board certification at the Institute for Diagnostic and Interventional Radiology at TUM, my medical degree from LMU Munich and my Master's Degree in Health Business Administration from FAU Nuremberg.
My group's research broadly focuses on the following topics:
I completed my post-doc in Artificial Intelligence with Professor Daniel Rueckert at the Department of Computing at Imperial College London, where I remain a visiting researcher.
Before dedicating myself to full-time AI research, I obtained my specialist diagnostic radiologist board certification at the Institute for Diagnostic and Interventional Radiology at TUM, my medical degree from LMU Munich and my Master's Degree in Health Business Administration from FAU Nuremberg.
My group's research broadly focuses on the following topics:
- Differential privacy and its applications to deep learning
- Trustworthy AI and AI alignment
- Generalisation, memorisation and training dynamics of neural networks
- Probabilistic machine learning techniques
- Federated learning
- Attacks against machine learning models
- Geometric deep learning and graph neural networks
- Biomedical applications and deployments, especially in medical imaging