The following contains currently open thesis topics in our areas of research. If you are interested in a topic or have a thesis idea of your own that might fit our research interests, please contact us directly.
Evaluation of effectiveness (e.g. accuracy) and efficiency of privacy-preserving approaches, compared to a base line of centralised learning. Application of approaches to new algorithms, data types, etc.
Evaluation of privacy protection, utility of the published data, novel attack mechanisms, application of differential privacy to machine learning models, …
Reinforcement learning can be used to train systems for sequential decision-making in cybersecurity tasks. This topic investigates how such approaches can improve system behavior.
Security monitoring systems rely on rules to detect threats. This topic explores how AI-based systems can assist in generating and maintaining detection rules.
Please contact Aljosha Judmayer.
This topic investigates how AI-based systems can support automated security testing and analysis.
Please contact Aljosha Judmayer.
Agent systems rely on external tools and skills (e.g., APIs, plugins, MCP servers). This topic investigates the implications of integrating such components into AI-based systems.
Please contact Aljosha Judmayer.
