AIF-C01 · Question #338
AIF-C01 Question #338: Real Exam Question with Answer & Explanation
The correct answer is B: Use Amazon Bedrock Guardrails content filters and denied topics.. Using Amazon Bedrock Guardrails' content filters and denied topics is the quickest and least effort solution to mitigate prompt injection attacks. These guardrails can be configured without model retraining, helping to automatically filter or block unsafe prompts and responses.
Question
A company is building a new generative AI chatbot. The chatbot uses an Amazon Bedrock foundation model (FM) to generate responses. During testing, the company notices that the chatbot is prone to prompt injection attacks. What can the company do to secure the chatbot with the LEAST implementation effort?
Options
- AFine-tune the FM to avoid harmful responses.
- BUse Amazon Bedrock Guardrails content filters and denied topics.
- CChange the FM to a more secure FM.
- DUse chain-of-thought prompting to produce secure responses.
Explanation
Using Amazon Bedrock Guardrails' content filters and denied topics is the quickest and least effort solution to mitigate prompt injection attacks. These guardrails can be configured without model retraining, helping to automatically filter or block unsafe prompts and responses.
Topics
Community Discussion
No community discussion yet for this question.