Yinpeng Chen
PhD Candidate
Tempe, Arizona, United States
Summary
👤
Senior🎓
Top SchoolYinpeng Chen is a PhD candidate in Electrical Engineering and Arts, Media and Engineering with around a decade of research and development experience spanning real-time multimedia systems, medical image registration, and computer vision. He has applied low-level languages and systems programming (C/C++, Objective-C, x86 assembly) to build production-oriented solutions such as a real-time license plate recognition system and a constraint-aware adaptation framework for multimedia. Internships at Microsoft Research Asia and IBM T. J. Watson Research Center reflect hands-on work delivering optimized video processing and parallelized 3D registration on specialized hardware. An active contributor to adversarial ML tooling, he implemented and refined attack methods in the widely used cleverhans library, showing a mix of theoretical ML interest and practical code maintenance. Based in Tempe and trained at Tsinghua and ASU, he combines rigorous academic research with a track record of shipping performant, deployable systems.
10 years of coding experience
8 years of employment as a software developer
Ph.D., Electrical Engineering/Arts, Media and Engineering, Ph.D., Electrical Engineering/Arts, Media and Engineering at Arizona State UniversityMaster, Electrical Engineering, Master, Electrical Engineering at Tsinghua University
Github Skills (8)
machine-learning10
adversarial-attacks10
tensorflow10
python10
security10
benchmark9
benchmarking9
numpy8
Programming languages (4)
Github contributions (5)
cleverhans-lab/cleverhans
Dec 2017 - Dec 2017
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Role in this project:
ML Engineer
ML EngineerContributions:5 commits, 3 PRs, 3 comments in 1 day
Contributions summary:Yinpeng primarily contributed to the `cleverhans` library by implementing and updating adversarial attack methods. Their work included adding the Momentum Iterative Method, along with its associated parameters and tests. Further commits refined this attack, including fixing typos and updating gradient calculations, demonstrating a focus on improving and maintaining the library's core functionality related to adversarial example generation.
benchmarkingrobustnessadversarial-machine-learningsecurityadversarial
dongyp13/Targeted-Adversarial-Attack
Oct 2017 - May 2018
Contributions:7 commits, 7 pushes, 1 branch in 7 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.