I am a fourth-year Computer Science PhD candidate at Cornell Tech, gratefully advised by Prof. Vitaly Shmatikov. Broadly, my interests are somewhere in the (vast) union of machine learning, security, privacy, and safety. Nowadays, my work is mainly split across two domains: (1) agentic security and (2) the (universal) geometry of embeddings.
Over the past eight years, I've had stints at MATS (with Google DeepMind), Google Research, and Microsoft, working on everything from alignment to control-flow integrity to detections for large-scale criminally-orchestrated attacks.
Before my PhD, received my master's and two bachelor's degrees (honors) from the University of Washington, Seattle. I was primarily advised by Prof. Sewoong Oh, and had the honor of spending time with Prof. Rajesh Rao, and Spencer Sevilla.