Projects

Current and past research projects of the lab.

Current projects

LADA: Localization-Aware Distributed Alignment

Making LLM guardrails robust, auditable and maintainable by finding where safety behavior lives inside the model and making it harder to break.

  • Interpretability
  • Robustness
  • Privacy
  • Evaluation

GENESIS-AI

A reflexive generative AI ecosystem for cybersecurity that builds governance, compliance and adaptive protection into a single architecture.

  • Robustness
  • Privacy
  • Evaluation