Prompt Shields and Harm Detection Quiz

5 questions Pass: 70% +25 pts (50 with Pro)

Quiz covering Implementing Responsible AI

What you'll be asked

  1. Which Azure AI service feature is specifically designed to detect and block 'jailbreak' attempts where a user tries to manipulate an AI model into ignoring its safety guidelines?
  2. A developer is building a chatbot and wants to ensure that the AI does not generate content that includes copyrighted text from external sources. Which feature should they implement?
  3. When configuring Content Safety filters, what is the purpose of setting a 'Severity Threshold'?
  4. You are implementing a multi-modal application that processes both text and images. How does Azure AI Content Safety handle this?
  5. A security auditor notices that a system is vulnerable to 'Indirect Prompt Injection,' where an attacker places malicious instructions in a document that the AI then summarizes. Which architectural pattern should be used to mitigate this?

Answers and explanations come after you submit.