Adversarial example vs Data poisoning

Why they differ

An adversarial example fools a finished model while it is in use; data poisoning corrupts the model while it learns.

AI risk & governance

An input altered on purpose, often in ways people cannot see, so that a trained AI model gives a confident but wrong answer.

Formal

An input to a trained machine learning model, usually a neural network, that an attacker has shifted by a small, calculated amount so that the output changes to a wrong or chosen answer at inference time; the model itself is not modified.

In plain English

Like an optical illusion made for a machine - a few dots a person would never notice make the computer see a cat as a toaster.

In practice

A municipality's IT operations manager finds that its AI-based malware filter can be fooled - changing a few unused parts of a harmful file, without touching what it does, makes the filter mark it as safe.

Why it matters

A model can pass every ordinary test and still fail against an opponent who shapes the input, so high accuracy says little about safety where AI filters malware, checks faces or steers vehicles.

Data poisoning

AI risk & governance

Slipping false or harmful examples into the data an AI learns from so that it later behaves the way an attacker wants.

Formal

An attack on the integrity of machine learning in which an attacker adds, changes or wrongly labels examples in the training data so that the finished model makes chosen mistakes, often only when a secret trigger appears.

In plain English

Like secretly swapping a few pages in a student's textbook - they study hard, pass most tests, but give the wrong answer exactly where the pages were changed.

In practice

A pension fund trains a model to spot false claims partly on a public collection of examples; an attacker has planted hundreds of cases there marked “honest”, so claims with the same pattern later pass unchecked.

Why it matters

The damage sits inside the model and stays hidden until the trigger appears, so organisations must know and control where every piece of their training data comes from.