About Me

I'm an AI security researcher at the Microsoft Security Response Center (MSRC) focused on LLM interpretability and AI security vulnerabilities. Previously, I also worked within MSRC as a threat hunter for advanced persistent threats across the foundational infrastructure running Azure, M365, and our identity services. My research currently focuses on AI security, Bayesian Learning, and Applied Algebraic Topology.

I am also a part-time student in the Department of Mathematics at Imperial College London, where I received the Marjorie McDermott MSc Scholarship. My MSc supervisor is Dr.Sarah Filippi. I also conduct research with Dr. Anthea Monod's Erlangen AI Hub, applying modern mathematics to understand the mathematical foundations of intelligence.

I want to understand the processes, structure, and higher order interactions that form the basis of cognition and good learning algorithms. I believe language occurs in thought and I'm driven to understand the form or representational substrate underlying our experience of thinking. My belief that meaning lies in structure (and not the words, symbols, concepts themselves) informs my approach to interpreting and securing AI systems. Ultimately, I'd like my work to contribute towards human brain regeneration - specifically when parts of the brain are removed or damaged.

I'm grateful for my journey and to everyone I've connected with along the way. I love languages and the process of learning through immersion. If you want to get in touch, please feel free to email me. I'd love to hear from you!

• Google Scholar
• GitHub