Thesis topic:
Cyber Deception Against AI-Driven Attack Agents
- Supervisor: Mubashar Iqbal
- contact: mubashar.iqbal@ut.ee
This thesis topic aims to create adaptive honeypots that identify LLM-directed attackers and alter the environment to waste their resources or expose their objectives.
- Research question: Can sequential behavior distinguish agentic attackers from scripted tools and humans?
- Contribution: A classifier plus reinforcement-learning deception policy.