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.

Cybersecurity Knowledge Graph Generation with LLMs

Machine Learning/AI and Security

Cybersecurity knowledge graphs (KGs) provide structured representations of threats, vulnerabilities, and attack techniques. This topic explores how LLMs and rule-based methods can be combined to construct, validate, and reason over cybersecurity knowledge graphs.

Goal / Research Questions:

  • How effectively can LLMs construct cybersecurity knowledge graphs from unstructured data?
  • How can hybrid approaches (LLMs + symbolic rules) improve correctness and consistency?
  • How can knowledge graphs be used to support automated cybersecurity reasoning? 

Please contact Andreas Ekelhart.

Back

To top