Exam AI-102 topic 8 question 12 discussion

Actual exam question from Microsoft's AI-102

Question #: 12
Topic #: 8

You have an Azure subscription that contains an Azure OpenAI resource named AI1.

You build a chatbot that uses AI1 to provide generative answers to specific questions.

You need to ensure that questions intended to circumvent built-in safety features are blocked.

Which Azure AI Content Safety feature should you implement?

A. Monitor online activity
B. Jailbreak risk detection
C. Moderate text content
D. Protected material text detection

Show Suggested Answer

Suggested Answer: B 🗳️

by cf1086a at Oct. 21, 2024, 5:21 p.m.

Comments

Submit Cancel

mbsff

Highly Voted 6 months, 1 week ago

Selected Answer: B

Now called Prompt shields for user Prompts https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection#prompt-shields-for-user-prompts

upvoted 5 times

pabsinaz

5 months, 4 weeks ago

Azure OpenAI offers a feature called Prompt Shields (formerly known as Jailbreak Risk Detection) to protect against harmful or inappropriate content generated by AI models. This feature helps detect and mitigate risks associated with both User Prompt Attacks and Document Attacks

upvoted 1 times

...

swap_c11

Most Recent 3 months, 2 weeks ago

Update to prompt shield

upvoted 1 times

...

syupwsh

3 months, 3 weeks ago

Selected Answer: B

B is CORRECT because it is specifically designed to detect and block user attempts to manipulate or circumvent the built-in safety mechanisms of an AI model. Here, the chatbot using AI1 relies on Azure OpenAI to provide generative responses. However, some users may try to bypass content restrictions by rephrasing their inputs, using adversarial prompts, or employing indirect queries to elicit responses that the AI is programmed to block.

upvoted 1 times

...