Concept information
Preferred term
adversarial example
Definition
- 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)
Broader concept
In other languages
-
French
-
exemple antagoniste
URI
http://data.loterre.fr/ark:/67375/8LP-CM1BL2SJ-B
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}