# Adversarial Example

> A tiny change made on purpose, so an AI gets it wrong.

**Field:** Artificial Intelligence  
**Category:** Safety & Security  
**Also known as:** Adversarial Attack, Adversarial Input, Evasion Attack

## Think of it like

It is like a trick drawing for a computer. You see a cat, but it sees a dog.

## Definition

An adversarial example is an input changed on purpose, often by a tiny bit, so a model gets it wrong. To a person, the photo or sound seems the same. But the change aims at the model's weak spots. So the answer flips, and the model is often very sure of it. In a famous case, faint noise was added to a photo of a panda, and the model said gibbon. Some work in the real world too, such as stickers on a stop sign that fool a camera.

## Example

Researchers put a few small stickers on a stop sign. People still read it as a stop sign, but a vision model reads it as a speed limit sign.

## Why it matters

Vision and speech models are used in cars, security and medicine. A cheap trick that fools them is a real danger.

## Common mistake

Testing only on normal inputs. A model that scores well on clean data can still be easy to fool on purpose.

## Three principles

- **Tiny change.** Big mistake.
- **Looks the same.** To a person.
- **Works for real.** Stickers, sounds.

## Related terms

- [Image Classification](https://learn.benibix.com/term/ai/image-classification)
- [Data Poisoning](https://learn.benibix.com/term/ai/data-poisoning)
- [Computer Vision](https://learn.benibix.com/term/ai/computer-vision)
- [AI Red Teaming](https://learn.benibix.com/term/ai/ai-red-teaming)

## Told apart from

- [Data Poisoning vs Adversarial Example](https://learn.benibix.com/compare/data-poisoning-vs-adversarial-example): People think data poisoning and adversarial examples are one attack. They are not. Poisoning strikes while the model is still learning. Bad examples go into what it learns from, and the harm is built in. An adversarial example strikes once the model is done. The model is fine. One input is changed so the model reads it wrong.

![A photo of a panda plus a faint pattern of noise looks the same to a person. The model now says gibbon, and is more sure than before.](https://learn.benibix.com/diagrams/sf-adversarial-example.svg)

---

Source: https://learn.benibix.com/term/ai/adversarial-example
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
