Dictionary · A Taxonomy and Terminology of Adversarial Machine Learning
L2 — definitions grouped by regulatory framework.
Nouns
8 senses- Transparency
Understanding the working logic of the model.
- Adversarial Example
Machine learning input sample formed by applying a small but intentionally worst-case perturbation ... to a clean example, such that the perturbed input causes a learned model to output an incorrect answer.
- attack
Action targeting a learning system to cause malfunction.
- Explanation
Systems deliver accompanying evidence or reason(s) for all outputs.
- Explainability
The ability to provide a human interpretable explanation for a machine learning prediction and produce insights about the causes of decisions, potentially to line up with human reasoning.
- Inference
The stage of ML in which a model is applied to a task. For example, a classifier model produces the classification of a test sample.
- Robustness
The ability of a machine learning model/algorithm to maintain correct and reliable performance under different conditions (e.g., unseen, noisy, or adversarially manipulated data).
- resilience
The ability to prepare for and adapt to changing conditions and withstand and recover rapidly from disruptions. Resilience includes the ability to withstand and recover from deliberate attacks, accidents, or naturally occurring threats or incidents. The ability of a system to adapt to and recover from adverse conditions.