Skip to content
AImpact
IT EN
Safety Intermediate Also known as: Esempio avversariale

Adversarial example

An input modified imperceptibly for a human but crafted to fool a model into producing a wrong or harmful output.

ShareLinkedInX

In practice

Born in vision (a few pixels can make a panda be classified as a gibbon), today it also hits LLMs with strange character suffixes that unlock forbidden behavior. It is an intrinsic vulnerability of neural networks.

Related terms

Seen in the wild

0 entries mentioning it

No archive entry mentions it explicitly. Appears in broader contexts.

← All terms