David Slater
Staff Researcher, GitHub Next
Tacoma, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolDavid Slater is a Staff Researcher at GitHub Next with nine years of applied machine learning experience focused on deep learning for code comprehension, malware detection, and biometrics. He transitioned through research and leadership roles at Two Six and Invincea before joining GitHub Copilot and now shapes forward-looking ML research for developer tools. David contributes to high-impact open-source security tooling, notably improving PyTorch support and robustness features in the Adversarial Robustness Toolbox. His background combines academic rigor from the University of Washington with hands-on cyber systems and vulnerability modeling experience at JHU APL and Boeing, giving him a rare blend of secure-systems intuition and production ML engineering. Based in Tacoma, he is known for turning adversarial and security challenges into practical model- and preprocessor-level defenses.
9 years of coding experience
15 years of employment as a software developer
Doctor of Philosophy Program (Unfinished), Electrical Engineering, Doctor of Philosophy Program (Unfinished), Electrical Engineering at University of Washington
Github Skills (6)
machine-learning10
pytorch10
python10
preprocessor9
ai9
tensorflow5
Programming languages (5)
Github contributions (5)
Trusted-AI/adversarial-robustness-toolbox
Jun 2020 - Nov 2022
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Role in this project:
ML Engineer
ML EngineerContributions:12 reviews, 20 commits, 7 PRs in 2 years 6 months
Contributions summary:David primarily contributed to the development and improvement of the Adversarial Robustness Toolbox (ART) library. Their work involved modifying existing code, specifically related to the PyTorch classifier, data preprocessors and postprocessors. Key contributions include optimizing predictions, updating preprocessor usage, bug fixes, and ensuring code consistency. They also worked on various aspects of the preprocessor, including gaussian augmentation, spatial smoothing, and implementing identity BPDA.
blueteaminferencemachine-learningpythonsecurity
twosixlabs/csl
Aug 2020 - Feb 2022
Cooperative Secure Learning
Contributions:11 commits, 8 PRs, 5 pushes in 1 year 6 months
securesecure-learningmachine-learningcooperative
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.