Han Xu
PhD Candidate
East Lansing, Michigan, United States
Summary
🤩
Rockstar🎓
Top SchoolHan Xu is a PhD candidate in Computer Science at Michigan State University with six years of experience focusing on machine learning research, particularly adversarial robustness for images and graphs. With a strong quantitative foundation from a statistics master's at the University of Michigan and a math BS from Nankai University, he brings rigorous mathematical thinking to practical ML engineering. Han contributes to the popular DeepRobust PyTorch library, implementing and refining attack and defense training pipelines and CNN model code. His work bridges research and reproducible tooling, emphasizing configurable training workflows and robust model implementations. Based in East Lansing, he combines academic depth with hands-on open-source development that accelerates adversarial ML experiments.
6 years of coding experience
Master's degree, Statistics, Master's degree, Statistics at University of Michigan - Rackham Graduate SchoolBachelor of Science (B.S.), math, Bachelor of Science (B.S.), math at Nankai UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at Michigan State University
Github Skills (10)
mask-rcnn10
faster-rcnn10
pytorch10
machine-learning10
adversarial-attacks10
deep-learning10
python9
deep-neural-networks9
neural-network9
mnist8
Programming languages (1)
Github contributions (5)
DSE-MSU/DeepRobust
Nov 2019 - Apr 2020
A pytorch adversarial library for attack and defense methods on images and graphs
Role in this project:
ML Engineer
ML EngineerContributions:68 commits, 40 pushes in 5 months
Contributions summary:Han's commits primarily involve modifying and updating files related to training and model development within the `deeprobust` repository, specifically focusing on adversarial attacks and defenses. The commits include adjustments to training scripts (`pgdtraining.py`), and model definitions (`CNN.py`). The user is also making changes to configuration files.
pytorchadversarial-attacksgraph-convolutional-networksdeep-learningadversarial
hannxu123/fair_robust
Jun 2021 - Apr 2022
Contributions:11 commits, 10 pushes, 1 branch in 10 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.