Georgios Kaissis

Technical University of Munich - Helmholtz Munich - Imperial College London


I am privileged to work with an amazing and diverse team of talented researchers

Current supervisions
  • Alex Ziller (PhD): Differentially private deep learning, privacy auditing, federated learning
  • Tamara Müller (PhD): Differentially private graph neural networks
  • Florian Hölzl (PhD): Equivariant CNNs for differential privacy, memorisation and generalisation
  • Jonas Kuntzer (PhD): Mechanistic interpretability, AI alignment, federated learning
  • Leonhard Feiner (PhD): Bayesian deep learning
  • Moritz Knolle (PhD): Training dynamics of differentially private neural networks, fairness
  • Johannes Kaiser (PhD): Individual privacy accounting, federated learning
  • Dmitrii Usynin (PhD): Attacks against privacy-preserving machine learning models (red-teaming)
  • Florent Dufour (PhD): Machine learning with trusted execution environments
  • Reihaneh Torkzadehmahani (PhD): Label-noise resistant learning, differentially private synthetic data generation, machine unlearning
  • Reza Nasirigerdeh (PhD): Federated learning, architecture design for differential privacy
  • Friederike Jungmann (MD): Human-in-the-loop machine learning
  • Johannes Brandt (MD): Medical imaging analysis with deep learning techniques
  • Philip Müller (PhD): Natural Language Processing, Multimodal (image/text) AI
  • Felix Meissen (PhD): Anomaly detection
  • Anneliese Riess (PhD): Mathematical foundations of differential privacy
  • Vasiliki Sideri-Lampretsa (PhD): Deep learning-assisted image registration
  • Rickmer Braren (TUM): Machine learning in Radiology
  • Johannes Paetzold (TUM, Imperial College): Machine learning on graphs
  • Ben Glocker (Imperial College): Fairness
  • Jamie Hayes (Google DeepMind): Differentially private machine learning
  • Borja Balle (Google DeepMind): Differentially private machine learning
  • Eleni Triantafilou (Google DeepMind): Machine unlearning
  • Stefan Kolek (LMU Munich): Mathematical foundations of AI and differential privacy
  • Gitta Kutyniok (LMU Munich): Mathematical foundations of AI and differential privacy
  • Dimitris Karampinos (TUM): Deep learning for magnetic resonance imaging
  • Kerstin Hammernik (TUM, NVidia): Complex-valued deep learning
  • Jan Böttcher (TUM): Deep learning in immunology
  • Daniel Truhn (UK Aachen): Privacy-preserving machine learning in radiology