A municipal leaf-collection brief defines a GenAI security vector as introducing data that disrupts the AI’s output — for example, an image that lures the model into another context and provokes hallucinated acceptance criteria. Which vector is that?
Select an answer to reveal the explanation.
Short Explanation
Request manipulation is the “poison the ask” vector — tainted input that knocks the reply off course. A misleading image that drags the model into inventing acceptance criteria fits that definition. It is about disrupted output, not the training-data extraction story.
Full Explanation
In syllabus v1.1, request manipulation means introducing data that disrupts the AI’s output, including multimodal examples that shift context and trigger hallucinated testware. Testers recognize the vector at a definition level and verify outputs against the real test basis. How-to guidance for planting fake rules is out of scope.