Nicholas Carlini
Postdoctoral Research Fellow at Utah Vascular Research Laboratory
United States
Summary
🤩
Rockstar🎓
Top SchoolNicholas Carlini is a postdoctoral research fellow and researcher with 14 years of experience at the intersection of human bioenergetics, vascular physiology, and machine learning security. Currently at the University of Utah School of Medicine, he investigates lifestyle and mechanistic interventions to counteract age- and disease-related vascular and metabolic dysfunction. He brings a rare combination of deep experimental physiology training (PhD in Human Bioenergetics) and hands-on ML security work—contributing to high-profile open-source projects like CleverHans and TensorFlow Privacy, where he explored adversarial attacks and privacy-preserving training techniques. Known for meticulous code quality and reproducible research, he has a track record of translating code fixes and attack implementations into clearer tutorials and robust tools. Outside the lab he has coached athletic performance and community health programs, reflecting a pragmatic commitment to applied human health.
14 years of coding experience
6 years of employment as a software developer
Bachelor's degree, Public Health, Bachelor's degree, Public Health at Salisbury UniversityPostdoctoral Research Fellow, Postdoctoral Research Fellow at University of Utah School of MedicineDoctor of Philosophy - PhD, Human Bioenergetics, Doctor of Philosophy - PhD, Human Bioenergetics at Ball State University
Github Skills (26)
algorithm10
algorithms10
adversarial-attacks10
python10
machine-learning10
data-structure10
keras10
adversarial-machine-learning10
privacy10
tensorflow10
fileio10
file-handling10
file-processing10
neural-network10
data-structures10
Programming languages (12)
Github contributions (5)
google-research/deduplicate-text-datasets
Jul 2021 - Jun 2022
Role in this project:
Back-end Developer
Back-end DeveloperContributions:40 commits, 6 PRs, 24 pushes in 10 months
Contributions summary:Nicholas primarily focused on refactoring and rewriting core functionalities of the project. They started with a v1 rewrite, implemented individual functions for each command, and introduced new argument parsing. Their work involved cleaning up warnings and improving clarity in the output, as well as fixing issues related to the suffix array construction and the merging process. The user also addressed errors in the count occurrences functionality.
carlini/nn_robust_attacks
Mar 2017 - Dec 2020
Robust evasion attacks against neural network to find adversarial examples
Role in this project:ML Engineer
ML EngineerContributions:18 commits, 9 PRs, 19 pushes in 3 years 9 months
Contributions summary:Nicholas primarily contributed to the project by addressing various issues related to the robustness of neural network attacks. Their work involved fixing code clean-up typos, improving confidence checks within the L2 attack implementation, and updating the MNIST model to Keras v2. They also modified the code to assert the attack's operation and removed dead code, showcasing a focus on code quality and model integrity.
neural-network
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.