Hannah Brown

I am an AI researcher focusing on safety, privacy, and trust in large langauge models. I obtained my PhD from the National University of Singapore in 2026. My thesis focused on trustworthy natural language processing—specifically on defining privacy leakage in large language models, discovering weaknesses and current model robustness, proposing defences to jailbreak attacks, and measuring factors important to LLM alignment. My interest in NLP comes from my background in sociolinguistics, which I try to incorporate into my research whenever possible.

Since graduating, my work focuses on the engineering side, improving the performance and safety of agentic AI in distributed settings.

In my free time, you can find me looking for new ways to ride a bicycle around Singapore, reading, running, or playing board games with friends.