- Generating obfuscating transformations with LLMs
- LLM-driven diversification to defeat pattern-based attacks
- Using LLMs as a "red team" oracle to evaluate the strength of applied protections
Please contact Sebastian Schrittwieser.
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.