Yao Qin
Research Scientist at Google
California, United States
Summary
👤
Senior🎓
Top SchoolYao Qin is a research scientist at Google with a decade of experience in adversarial examples, computer vision, and general machine learning, grounded in a PhD from UC San Diego. He has a strong track record of industrial research internships across Google, Microsoft, and NEC Labs, including work with prominent advisors like Geoffrey Hinton and Ian Goodfellow. At Google he focuses on robust ML, translating academic adversarial-attack techniques into practical defenses and evaluations for real-world systems. His open-source contributions to the well-known CleverHans adversarial library include ASR-specific attacks, room reverberation modeling, and perceptual masking features that strengthen speech-model robustness. Comfortable at the intersection of theory and applied engineering, he brings both rigorous experimental methodology and production-minded implementation skills. Based in California, he combines deep academic training with hands-on work hardening models used in deployed systems.
10 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of California San DiegoMaster's degree, Computer Science, Master's degree, Computer Science at University of California, San DiegoBachelor's degree, Electrical, Electronics and Communications Engineering, Bachelor's degree, Electrical, Electronics and Communications Engineering at Dalian University of Technology
Github Skills (10)
adversarial-machine-learning10
machine-learning10
speech-recognition10
benchmarking10
benchmark10
tensorflow10
automatic-speech-recognition10
python10
asr10
security10
Programming languages (2)
Github contributions (5)
cleverhans-lab/cleverhans
Jun 2019 - Jun 2019
An adversarial example library for constructing attacks, building defenses, and benchmarking both
Role in this project:
ML Engineer
ML EngineerContributions:35 commits, 12 PRs, 2 comments in 2 days
Contributions summary:Yao primarily contributed to the development and testing of adversarial example techniques within the context of Automatic Speech Recognition (ASR). They added and modified files related to generating and testing robust adversarial examples, including scripts for generating perturbations and evaluating model performance against them. Key contributions involved the implementation of speech room reverberation to strengthen the model against imperceptible attacks. The user also added features and integrated functionalities such as masking thresholds and the creation of features utilizing TF, likely for the attack strategies.
benchmarkingrobustnessadversarial-machine-learningsecurityadversarial
yaq007/Autofocus-Layer
May 2018 - Mar 2019
Contributions:13 commits, 19 pushes, 7 comments in 9 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.