Generative AI at Work / Unit 7 GAI 159 short lesson, about 20 seconds
Poisoned Data
Captions available
The idea
Data poisoning, one of the attacks NIST lists against generative AI, corrupts the data a model learns from or retrieves, so that its outputs change in ways the attacker intends.
In practice
Planted pages in a document collection that steer an internal assistant toward a fake supplier's contact details.
Where people slip
A tool that reads from a shared library inherits whatever was planted in it.
Your place on the trail
Every lesson rests on earlier ones and opens later ones. Tap any to jump.
Builds on
Unlocks
- Nothing yet depends on this.
Something wrong in this lesson? Flag it · Sources for Generative AI at Work