Concept graph
Glossary
Short definitions with deeper context and cross-links to sibling terms.
Machine Learning
Adversarial Training
Adversarial training improves model robustness by training on deliberately perturbed inputs that are designed to expose failures under a defined threat model.
Model Evaluation
Robustness
The ability of a model to maintain performance despite variations in input data or conditions.
Model Evaluation
Robustness Testing
Evaluating how well a model performs under various adversarial conditions.