About

I am a researcher bridging computer security and machine learning. My work focuses on enhancing the safety, security, and alignment of advanced AI systems. I develop defenses against adversarial attacks and apply large language models to binary analysis and reverse engineering.

I am a Ph.D. student at Sungkyunkwan University, advised by Hyungjoon (Kevin) Koo. I hold a B.A. and M.S. in software from the same institution.

My main research interests include adversarial robustness in advanced AI systems (like RAG and A2A communication) and using LLMs for cybersecurity challenges such as binary analysis and reverse engineering.

A complete list of my publications are online, along with some of my code, and some extra writings.