AIF-C01: AWS Certified AI Practitioner

AIF-C01: AWS Certified AI Practitioner practice questions, page 6 of 22, with answer review and explanations.

Question 26

A security company is using Amazon Bedrock to run foundation models (FMs). The company wants to ensure that only authorized users invoke the models. The company needs to identify any unauthorized access attempts to set appropriate AWS Identity and Access Management (IAM) policies and roles for future iterations of the FMs. Which AWS service should the company use to identify unauthorized users that are trying to access Amazon Bedrock?

  1. AWS Audit Manager
  2. AWS CloudTrail
  3. Amazon Fraud Detector
  4. AWS Trusted Advisor

Question 27

A company has developed an ML model for image classification. The company wants to deploy the model to production so that a web application can use the model. The company needs to implement a solution to host the model and serve predictions without managing any of the underlying infrastructure. Which solution will meet these requirements?

  1. Use Amazon SageMaker Serverless Inference to deploy the model.
  2. Use Amazon CloudFront to deploy the model.
  3. Use Amazon API Gateway to host the model and serve predictions.
  4. Use AWS Batch to host the model and serve predictions.

Question 28

An AI company periodically evaluates its systems and processes with the help of independent software vendors (ISVs). The company needs to receive email message notifications when an ISV's compliance reports become available. Which AWS service can the company use to meet this requirement?

  1. AWS Audit Manager
  2. AWS Artifact
  3. AWS Trusted Advisor
  4. AWS Data Exchange

Question 29

A company wants to use a large language model (LLM) to develop a conversational agent. The company needs to prevent the LLM from being manipulated with common prompt engineering techniques to perform undesirable actions or expose sensitive information. Which action will reduce these risks?

  1. Create a prompt template that teaches the LLM to detect attack patterns.
  2. Increase the temperature parameter on invocation requests to the LLM.
  3. Avoid using LLMs that are not listed in Amazon SageMaker.
  4. Decrease the number of input tokens on invocations of the LLM.

Question 30

A company is using the Generative AI Security Scoping Matrix to assess security responsibilities for its solutions. The company has identified four different solution scopes based on the matrix. Which solution scope gives the company the MOST ownership of security responsibilities?

  1. Using a third-party enterprise application that has embedded generative AI features.
  2. Building an application by using an existing third-party generative AI foundation model (FM).
  3. Refining an existing third-party generative AI foundation model (FM) by fine-tuning the model by using data specific to the business.
  4. Building and training a generative AI model from scratch by using specific data that a customer owns.