
About Me

I am a third year Computer Science Ph.D. student at Stanford University advised by Alex Aiken. I received my bachelor’s degree in Computing from the College of Creative Studies at UC Santa Barbara, where I worked with Giovanni Vigna and Christopher Kruegel on binary analysis and decompilation as a member of the Seclab. I am grateful to be supported by an NSF Graduate Research Fellowship.
Contact Info
I’m always happy to talk about research, teaching, or anything else! You can email me at unger@stanford.edu.
Research
I’m broadly interested in compilers, program analysis, and optimization, especially in emerging applications such as machine learning. My current research focuses on hardware-aware optimization of deep learning workloads. Recently I have worked on accelerating distributed deep neural network training.
Teaching
During my final year at UCSB I had the opportunity to develop and lead two quarters of CMPSC 595G, a graduate seminar affectionately referred to as “hack meetings” by its students. Links to the archived class webpages are below:
- CMPSCS 595G (F19): Advanced Reverse Engineering and Binary Exploitation
- CMPSCS 595G (W20): Topics in Automated Binary Analysis
Note: Currently the class assignments/challenges are down. I will get them running again at some point, but if you want to access them before this point please email me directly.
Recent: 2 of the top 10 2020 CSAW North America CTF finalist teams included students who were in these classes. I certainly can’t claim any credit for their success, but congratulations to Nathan Wachholz, Chaofan Shou, and Qi Su!
Publications
- C. Unger, Z. Jia, W. Wu, S. Lin, M. Baines, C. E. Q. Narvaez, V. Ramakrishnaiah, N. Prajapati, P. McCormick, J. Mohd-Yusof, X. Luo, D. Mudigere, J. Park, M. Smelyanskiy, and A. Aiken. Accelerating DNN Training Through Joint Optimization of Algebraic Transformations and Parallelization. USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2022. pdf, slides, extended slides, recording
- C. Spensky, A. Machiry, N. Redini, C. Unger, G. Foster, E. Blasband, H. Okhravi, C. Kruegel, G. Vigna. Conware: Automated Modeling of Hardware Peripherals. Asia CCS 2021: ACM ASIA Conference on Computer and Communications Security.
- E. Gamage, J. Greenfield, C. Unger, S. Kamali, J. Clark, C. Harmer, L. Luo, J. Wang, M. Shatruk, K. Kovnir. Tuning Fe-Se Tetrahedral Frameworks by Combination of [Fe(en)3]2+ Cations and Cl- Anions. Inorganic Chemistry. 59(18): 13353-13363, 2020.
- J. Greenfield, C. Unger, M. Chen, N. Izquierdo, K. Woo, O. Garlea, S. Kamali, K. Kovnir. A series of chiral, polar, homospin topological ferrimagnets: M3(OOCH)5Cl(OH2) (M = Fe, Co, Ni). Chemistry of Materials. 29(18): 7716-7724, 2017.
Talks
- Legion Retreat 2022: slides
Past/Current Projects
- FlexFlow: Automatic discovery of fast parallelization strategies for distributed deep neural network training
- CodeSentry: a tool to identify embedded library components in binaries, now available as a commercial product (research intern in 2019 and 2020 supervised by Vineeth Kashyap)
- angr core developer (esp. angr-platforms, angr-management, and decompiler)
- Lead organizer of the 2019 and 2020 iCTFs
- kuin: Web-based network monitoring and analysis system for attack-defense CTFs
Affiliations
- Stanford (2020–)
- Shellphish (2016–)
- UCSB Seclab (2017–2020)
- Peters Lab (2017)
- Xu Du Lab (2015)
- Kovnir Lab (2014–2016)