AI engineering glossary · Evals guardrails AI security
What is adversarial example?
Adversarial example (also called adversarial input): An input altered by a tiny, often imperceptible change that makes a model give a wrong answer with high confidence, for instance an image with faint noise that flips its label. It reveals that models can rely on fragile patterns.
Adversarial example: an example
Adding faint noise to a photo of a stop sign makes an image classifier read it as a speed-limit sign.
Related terms
More Evals guardrails AI security terms
- Adversarial robustness
- Adversarial suffix
- Adversarial test set
- Adversarial training
- Answer relevancy
- Attack success rate
- Attack surface
- Automated red teaming
Where you learn it
Adversarial example is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.