Abigail Goldsteen
Senior Research Scientist at IBM
Israel
Summary
🤩
Rockstar🎓
Top SchoolAbigail Goldsteen is a Senior Research Scientist at IBM with about six years of hands-on experience focused on data security and privacy in machine learning. She has contributed to the well-known Trusted-AI Adversarial Robustness Toolbox by implementing black-box and white-box attribute inference attacks and integrating membership inference methods, blending research rigor with practical tooling. Based in Israel and educated at the Technion, she brings a strong academic foundation to applied ML security challenges inside a large enterprise. Her background includes long-term roles at IBM and early practical experience at Intel, reflecting a steady progression from student engineer to research staffer. Colleagues rely on her to translate adversarial research into testable, production-aware implementations that strengthen model defenses.
6 years of coding experience
Bachelor of Science (BSc), Bachelor of Science (BSc) at Technion - Israel Institute of Technology
Github Skills (9)
mle10
scikit-learn10
adversarial-machine-learning10
machine-learning10
python10
ml10
scikit10
pytorch9
tensorflow7
Programming languages (1)
Github contributions (5)
Trusted-AI/adversarial-robustness-toolbox
Apr 2020 - Jan 2023
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:41 reviews, 262 commits, 45 PRs in 2 years 8 months
Contributions summary:Abigail implemented initial versions of attribute inference attacks within the Adversarial Robustness Toolbox (ART) library, targeting machine learning models. Their contributions focused on developing both black-box and white-box attribute inference attack implementations, involving the creation of attack models and associated tests. They also focused on improving the integration of new membership inference methods with the codebase.
extractionpythonfairness-mlrobustnessadversarial-machine-learning
abigailgold/adversarial-robustness-toolbox
Apr 2020 - Oct 2024
Python library for adversarial machine learning (evasion, extraction, poisoning, verification, certification) with attacks and defences for neural networks, logistic regression, decision trees, SVM, gradient boosted trees, Gaussian processes and more with multiple framework support
Contributions:246 pushes, 45 branches in 4 years 6 months
boosted-treesextractionpythonfairness-mladversarial-machine-learning
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.