Beat Buesser
Machine Learning Engineer at IBM
Summary
🤩
RockstarBeat Buesser is a Machine Learning Engineer with seven years of experience specializing in AI, security, and privacy research at IBM Research. He contributes to high-impact open source projects such as the Adversarial Robustness Toolbox, improving PyTorch adversarial attacks and cross-framework integrations for TensorFlow and Keras. His work blends research-grade model security expertise with practical engineering—enhancing attack implementations, adding functionality, and integrating instrumentation like TensorBoard summary writers. Based in Ireland, he brings a research staff perspective to production-ready ML tooling and a track record of making complex adversarial techniques more usable across ecosystems. An underappreciated strength is his fluency across ML frameworks, enabling seamless improvements that benefit both red-team research and blue-team defenses.
7 years of coding experience
Github Skills (9)
pytorch10
adversarial-machine-learning10
machine-learning10
python10
tensorflow9
deep-learning9
computer-vision8
keras8
tensorboard7
Programming languages (3)
Github contributions (5)
Trusted-AI/adversarial-robustness-toolbox
Jan 2019 - Jan 2023
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Role in this project:
ML Engineer & Backend Developer
ML Engineer & Backend DeveloperContributions:48 releases, 2013 reviews, 4811 commits in 4 years 1 month
Contributions summary:Beat Buesser's contributions primarily focused on enhancements to the Adversarial Robustness Toolbox, a Python library for machine learning security. His work involved significant updates to the PyTorch implementation of the Adversarial Texture attack, with code changes that included the addition of new parameters and improved functionality. Beyond this, he also contributed fixes and improvements in the KerasClassifier and made adjustments to the TensorFlow codebase, indicating a broad involvement in the project's machine learning components and underlying frameworks. Furthermore, he also worked on the code to integrate with the summary writer for TensorBoard.
extractionpythonfairness-mlrobustnessadversarial-machine-learning
retr0-13/adversarial-robustness-toolbox
Jun 2021 - Feb 2022
Contributions:22 commits in 8 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.