About Me

Hello! I am an undergraduate researcher studying under Professor Sanghyun Hong within the Secure AI systems Lab (SAIL) at Oregon State University. My broad research interest is trustworthy machine learning, aiming to audit and improve the robustness of machine learning systems to adversarial threats and misuse. My recent work has focused on developing attacks to study the vulnerability of several machine learning systems, namely large language models and neural architecture search algorithms. I am expected to start my PhD in Fall 2025 (advised by Professor Sanghyun Hong) with a focus on improving our understanding of large language models in adversarial settings.