About Me

I am a software engineering PhD student and NSF Graduate Research Fellow at Carnegie Mellon University. I am fortunate to be advised by Dr. Claire Le Goues and work with Dr. Edward Schwartz at the CMU Software Engineering Institute. My work is in AI/ML, program analysis, and software security. In particular, I focus on NLP and reverse engineering.

A major theme of my recent work has been studying and building an ecosystem of software tools in support of neural decompilation. Decompilers convert compiled programs back into source code; neural decompilation enhances decompilation with machine learning to make the painstaking process of reverse engineering easier. In particular, in my work, I have:

• Built state-of-the-art neural-decompilers. (paper)
• Designed a new multifaceted paradigm-shifting evaluation technique to measure neural decompilers’ correctness and their value added over traditional decompilers. (paper)
• Systematically motivated the need for neural decompilation. (paper)
• Studied dataset quality and best practices for dataset construction. A machine learning model is only as good as its training data. (paper, paper)

Outside of neural decompilation, I have interned at GitHub, served on CMU’s REU-SE admissions comittee, and reviewed for ACM TOSEM.