AI-103 Certification Practice Question #24

Question

Note: This section contains one or more sets of questions with the same scenario and problem. Each question presents a unique solution to the problem. You must determine whether the solution meets the stated goals. More than one solution in the set might solve the problem. It is also possible that none of the solutions in the set solve the problem.
After you answer a question in this section, you will NOT be able to return. As a result, these questions do not appear on the Review Screen.
You have a multimodal AI generative model that accepts image uploads and uses extracted image text to generate responses.
You discover that users can upload unsafe images and embed hidden instructions into images to manipulate the model.
You need to implement controls to mitigate the risk.
Solution: You configure image moderation to block unsafe content before processing the images.
Does this meet the goal?

Accepted Answer

The scenario states users upload unsafe images. Azure AI Content Safety image (and multimodal) moderation scans and filters image content for inappropriate or harmful visuals and can block it before the model processes the image — exactly the control described in the solution. This directly mitigates the unsafe-image prong of the stated risk, so the solution meets the goal (Yes). Confidence is in the low-80s: there are no community votes, but image moderation maps cleanly to the "block unsafe content before processing the images" wording and to MS Learn's documented image-moderation feature, making this the most clear-cut Yes of the series.

More AI-103 practice questions