Adversarial Example

nounverified·updated May 18, 2026

GlossaryL1 — what DictionaryL2 — how used ThesaurusL3 — relations Universaleverything

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.

Framework senses

2 senses across 2 frameworks

A Taxonomy and Terminology of Adversarial Machine Learning1 senseview framework →

§1: 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.

Principal component adversarial example1 senseview framework →

§1: Samples generated from real samples with carefully designed imperceptible perturbations