Skip to main

Vocabulary of natural language processing (POC)

Search from vocabulary

Concept information

Término preferido

adversarial example  

Definición

  • 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. (NIST, The Language of Trustworthy AI: An In-Depth Glossary of Terms, 2023)

Concepto genérico

En otras lenguas

URI

http://data.loterre.fr/ark:/67375/8LP-CM1BL2SJ-B

Descargue este concepto:

RDF/XML TURTLE JSON-LD última modificación 12/6/24