Nicholas is a research scientist at Google DeepMind (formerly at Google Brain) working at the intersection of machine learning and computer security. His most recent line of work studies properties of neural networks from an adversarial perspective. Nicholas received a Ph.D. from UC Berkeley in 2018 and a B.A. in computer science and mathematics (also from UC Berkeley) in 2013.
Nicholas is generally interested in developing attacks on machine learning systems; most of his work focuses on demonstrating the security and privacy risks of these systems. For this work, he has received best paper awards at IEEE S&P (once), USENIX Security (twice), and ICML (three times). His work has been featured in public media, with coverage from the New York Times, the BBC, Nature Magazine, Science Magazine, Wired, and Popular Science.
When not otherwise busy with research, Nicholas writes lots of useless code ranging from an obfuscated Tic-Tac-Toe Game written in a single call to printf (which won the IOCCC 2020 Best of Show), to a Doom clone in 13k of WebGL + JavaScript, to a fully functional CPU built on top of Conway's Game of Life.
