Exam AI-103 Topic 1 Question 66 Discussion
Actual exam question for Microsoft's AI-103 exam
Question #: 66
Topic #: 1
Question #: 66
Topic #: 1
You have an app named App1 that uses a Microsoft Foundry multimodal model deployment.
App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context.
Some uploaded images contain embedded text.
You need to prevent potentially malicious instructions from being processed by the model.
What should you use?
App1 runs optical character recognition (OCR) on uploaded images and appends the OCR output to the prompt as additional context.
Some uploaded images contain embedded text.
You need to prevent potentially malicious instructions from being processed by the model.
What should you use?
Suggested Answer: B Vote an answer
To prevent potentially malicious instructions embedded within untrusted external sources (such as text extracted from uploaded images via OCR) from being processed by the model, you should use Prompt Shields for Documents (specifically designed for Indirect Prompt Attacks or Cross- Domain Prompt Injections).
Key Features to Implement
Prompt Shields for Documents: This specific component of Azure AI Content Safety / Prompt Shields analyzes external data--like text pulled from files, emails, or OCR outputs--appended to the prompt. It identifies and neutralizes hidden adversarial instructions trying to trick the model into overriding its system protocols.
Spotlighting: A native capability within Microsoft Foundry's Prompt Shields, Spotlighting uses advanced text-formatting techniques to separate valid user commands from the untrusted document text. This prevents the model from mistaking malicious instructions embedded inside the OCR output for instructions from the developer or end-user.
Reference:
https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/azure-ai-announces-prompt-shields-ga/4236033
Key Features to Implement
Prompt Shields for Documents: This specific component of Azure AI Content Safety / Prompt Shields analyzes external data--like text pulled from files, emails, or OCR outputs--appended to the prompt. It identifies and neutralizes hidden adversarial instructions trying to trick the model into overriding its system protocols.
Spotlighting: A native capability within Microsoft Foundry's Prompt Shields, Spotlighting uses advanced text-formatting techniques to separate valid user commands from the untrusted document text. This prevents the model from mistaking malicious instructions embedded inside the OCR output for instructions from the developer or end-user.
Reference:
https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/azure-ai-announces-prompt-shields-ga/4236033
by Albert at Jul 23, 2026, 07:29 AM
0
0
0
10
Comments
Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.
Report Comment
Commenting
You can sign-up / login (it's free).