Adversarial Robustness ToolboxThe Linux Foundation
Open sourceOpen source library for evaluating and defending machine learning models against adversarial attacks.
Adversarial Robustness Testing Tools
Ranking methodology
In development — no version effective yet.
Decision archetype: security · Scores are category-relative (P-01) and commercial relationships never affect rank (P-04).
Tools (3)
FoolboxUniversity of Tuebingen
Open sourceOpen source Python library for creating adversarial attacks on machine learning models.
Microsoft CounterfitMicrosoft
Open sourceOpen source automation tool for security testing of machine learning systems.
Some filter definitions for this category are not yet linked to a data field and are hidden until they are.