Yaxin Li
Advanced AI Research Scientist at Accenture
East Lansing, Michigan, United States
Summary
🤩
Rockstar🎓
Top SchoolYaxin Li is an Advanced AI Research Scientist and PhD candidate at Michigan State University with seven years of experience focused on adversarial machine learning and deep learning security. Currently at Accenture after research internships at Baidu and NewsBreak, she blends rigorous academic research with practical engineering—contributing adversarial attacks (CW, DeepFool, FGSM, PGD) and adversarial training tooling to the widely used DeepRobust library. She has taught C++ and database courses, mentored students, and published work modeling misinformation diffusion from her Tsinghua and MSU roots. Known for translating theoretical attacks into reproducible code, she brings a rare combination of threat-aware ML expertise and hands-on implementation that informs both research and production risk mitigation.
7 years of coding experience
5 years of employment as a software developer
High School, Science, High School, Science at Beijing No.4 High SchoolBachelor of Engineering - BE, Automation, Bachelor of Engineering - BE, Automation at Tsinghua UniversityDoctor of Philosophy - PhD, Doctor of Philosophy - PhD at Michigan State University
Github Skills (4)
adversarial-machine-learning10
pytorch10
machine-learning9
computer-vision9
Programming languages (1)
Github contributions (5)
DSE-MSU/DeepRobust
Sep 2019 - Nov 2022
A pytorch adversarial library for attack and defense methods on images and graphs
Role in this project:
ML Engineer
ML EngineerContributions:2 reviews, 399 commits, 19 PRs in 3 years 2 months
Contributions summary:Yaxin primarily contributed to the development of adversarial attack methods within the DeepRobust library, specifically implementing Carlini-Wagner, DeepFool, FGSM, and PGD attacks. They also worked on the creation of a data preparation tool for adversarial training. These contributions suggest a focus on practical application of adversarial attacks and robust training techniques within the context of image and graph deep learning.
pytorchadversarial-attacksgraph-convolutional-networksdeep-learningadversarial
YaxinLi0-0/Black-Box-Attacks
Sep 2021 - Nov 2022
Contributions:27 commits, 12 pushes in 1 year 1 month
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.