MSc Thesis: Privacy-preserving Deep Learning in Medical Imaging

Privacy-preserving artificial intelligence techniques such as differential privacy, encryption and multi-party computation can reconcile the needs for data utilisation and data protection in the medical domain, as mandated by legal and ethical requirements. Their widespread utilisation requires innovations in the fields of distributed machine learning (federated learning) as well as answering open questions in privacy research and cryptography.

We are seeking an MSc candidate with a strong background in machine learning, preferrably with previous exposure to medical imaging topics to complete their thesis at our institute. Experience with distributed systems, privacy and security issues or cryptology is desirable. We are offering an engaging work environment, a large, diverse team, close personal supervision and collaboration with AI, medical and privacy-preserving ML experts.

We can accommodate a wide range of interests from your side! Please get in touch with us to find an appropriate topic. We are also able to supervise guided research projects, smaller in scope than full MSc theses.

Georgios Kaissis
Georgios Kaissis
Senior Research Scientist

My research interests include image analysis, secure and private artificial intelligence and probabilistic modelling.