I am a PhD student at Georgia Tech advised by Polo Chau as a part of the Polo Club of Data Science.

My research is in the field of Trustworthy, Responsible, and Secure AI. My PhD thesis aims to identify vulnerabilities in AI systems and develop practical, scalable defenses against them, with the goal of securing large-scale AI models and increasing trust in the deployed systems. My work has produced two patents and two industry-deployed defenses along with papers at multiple top tier AI conferences. My work includes VISOR and VISOR++ which create a universal, transferable steering image that can steer architecturally diverse models without requiring access to their internal model parameters at runtime.

I have collaborated with scientists at IBM, HiddenLayer, Intel Labs, and Nanyang Technological University