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.
Please contact Sebastian Schrittwieser.
Cybersecurity data is often scarce or sensitive. This topic investigates how generative models can be used to create synthetic data for training and evaluation.
Cybersecurity knowledge evolves over time (e.g., vulnerabilities, attack campaigns). This topic investigates how temporal dynamics can be modeled, maintained, and updated in cybersecurity knowledge graphs.
LLMs often produce outputs that are difficult to verify. This topic investigates methods for improving trustworthiness through structured validation and grounding in trusted knowledge sources.
Please contact Aljosha Judmayer.
Managing vulnerabilities requires analyzing large volumes of data. This topic explores how AI systems can support vulnerability prioritization and analysis.
Evaluation of schemes for their robustness of attacks, vs. their data utility, e.g. measured by effectiveness in machine learning tasks
