AIP-C01 AI Safety Security And Governance Practice Test 2 — 15 Questions

Question 1

A company is using Amazon Q Business. How can they restrict access to specific data sources for different groups of users?

Accepted Answer

Configure ACLs in the data source connector. Amazon Q Business respects access control lists (ACLs) configured in the data source connector, so documents are only surfaced to users who have permission in the source system. When the connector indexes content, it ingests ACL information and enforces it at query time, ensuring each user sees only authorized data. This is the correct mechanism for restricting access to specific data sources per user group.

Answer

Create separate Amazon Q applications

Answer

Manually delete documents for specific users

Answer

Apply IAM policies to the user's login

Question 2

A firm wants to audit the specific version of a foundation model used for every inference request. How can they achieve this?

Accepted Answer

Enable Bedrock Model Invocation Logging. Bedrock Model Invocation Logging captures each invocation's request and response metadata — including the model ID and, when applicable, the specific model version or inference profile — and delivers it to CloudWatch Logs or S3. This provides the audit trail needed to prove which foundation model version handled each request.

Answer

Query Amazon SageMaker Model Monitor

Answer

Enable CloudTrail logs

Answer

Use AWS Config to track model changes

Question 3

You need to ensure that all data sent to an Amazon Bedrock model is encrypted in transit using private connectivity. What is the recommended service?

Accepted Answer

AWS PrivateLink (VPC Endpoints). AWS PrivateLink (VPC Endpoints) is the recommended service because it creates a private, one-way connection between a VPC and Amazon Bedrock using interface endpoints powered by ENIs, keeping traffic on the AWS backbone and off the public internet. This satisfies the requirement for private connectivity with encryption in transit (TLS) to the Bedrock endpoint. It avoids the need for internet gateways, NAT devices, or public IPs.

Answer

AWS WAF

Answer

AWS CloudFront

Answer

AWS Certificate Manager

Question 4

Which AWS tool is used to monitor the performance and latency of an application calling Bedrock?

Accepted Answer

Amazon CloudWatch. Amazon CloudWatch provides metrics for request latency, invocation count, and errors for Bedrock models.

Answer

Amazon Inspector

Answer

AWS CloudTrail

Answer

AWS Config

Question 5

A company requires that every AI-generated document must include a watermark for traceability. How can this be handled in Bedrock?

Accepted Answer

Use a custom post-processing Lambda function to inject metadata. Bedrock does not natively support watermarking of generated text, so the correct approach is to intercept the model response and apply a custom post-processing step — typically an AWS Lambda function — that injects a watermark, metadata tag, or traceable identifier into the output. This gives the company full control over the watermark format and ensures every generated document carries the required traceability marker.

Answer

Use fine-tuning to force the model to watermark

Answer

Enable watermarking in the Bedrock console settings

Answer

Use AWS KMS to sign the generated text

Question 6

A team wants to track who accessed a model and when. Which service provides this audit log?

Accepted Answer

AWS CloudTrail. AWS CloudTrail records API activity in an AWS account, including who made a request, when, from which IP, and which resources were affected. For tracking who accessed a model and when, CloudTrail captures the InvokeModel API calls (and related Bedrock API actions) with the identity of the caller. This makes it the correct service for audit logging of model access.

Answer

AWS Config

Answer

Amazon GuardDuty

Answer

Amazon CloudWatch

Question 7

A team is storing sensitive documents for RAG. They need to ensure that the document chunks in the vector database are encrypted at rest. How?

Accepted Answer

Configure the vector database (e.g., OpenSearch) with KMS encryption. Encryption at rest for a vector database is enforced at the storage layer of that database, so configuring the vector store (e.g., Amazon OpenSearch Serverless or Aurora pgvector) with a KMS customer-managed key ensures the indexed embeddings and metadata are encrypted on disk. This is independent of how the source documents are encrypted in S3. KMS CMKs give the team control over key rotation and access policies.

Answer

Use TLS for all connections

Answer

Use Amazon S3-managed encryption

Answer

Encrypt the source S3 bucket only

Question 8

To prevent accidental deletion of a Knowledge Base, which feature should be applied?

Accepted Answer

Apply an IAM policy denying DeleteKnowledgeBase. Apply an IAM policy denying DeleteKnowledgeBase. AWS Identity and Access Management (IAM) policies are the primary mechanism for controlling access to AWS actions, including the DeleteKnowledgeBase action for Amazon Bedrock Knowledge Bases. By explicitly denying this action, you prevent any principal (user, role, or service) from deleting the knowledge base, even if they have other permissions that would otherwise allow it. This is a direct, preventive control that aligns with the principle of least privilege.

Answer

Use AWS Backup

Answer

Enable MFA Delete on S3

Answer

Enable S3 Versioning

Question 9

An organization is concerned about 'Model Hallucinations' and needs a way to ground model outputs in trusted company documents. Which service supports this?

Accepted Answer

Amazon Bedrock Knowledge Bases. Amazon Bedrock Knowledge Bases implements Retrieval Augmented Generation (RAG) by connecting foundation models to trusted data sources stored in Amazon S3 or other supported repositories. It chunks, embeds, and indexes documents into a vector store, then retrieves relevant passages at inference time so the model's response is grounded in actual company content rather than parametric memory. This directly reduces hallucinations by supplying factual context in the prompt.

Answer

Amazon SageMaker Feature Store

Answer

AWS Glue Data Catalog

Answer

Amazon DynamoDB

Question 10

A developer needs to share a Bedrock prompt template with another team securely. What is the recommended method?

Accepted Answer

Use Amazon Bedrock Prompt Management. Amazon Bedrock Prompt Management provides a secure, centralized way to create, version, and share prompt templates with other teams. It integrates with IAM for access control, allowing you to grant specific permissions to other teams without exposing the prompt publicly. This is the recommended method for secure sharing.

Answer

Save the prompt as a text file in S3 with public access

Answer

Send the prompt in an email

Answer

Store the prompt in a Git repository without encryption

Question 11

You are building a chat application and notice sensitive internal data is leaking in responses. You have enabled Guardrails. What else should be checked?

Accepted Answer

Review the system prompt and the Knowledge Base document retrieval filters. Guardrails filter model inputs and outputs, but they do not control what data enters the prompt in the first place. If sensitive internal data is leaking, the likely sources are the system prompt (which may contain secrets or instructions that surface data) or the Knowledge Base retrieval filters (which may be returning documents the user should not see). Reviewing both is the correct next step.

Answer

Change the foundation model provider

Answer

Increase the temperature setting

Answer

Check if the model is fine-tuned on public data

Question 12

A company is using a third-party model via Bedrock and needs to ensure that the model provider does not use their data to train their base models. What must they do?

Accepted Answer

Understand that AWS does not use customer data to train their foundation models. AWS does not use customer data to train its foundation models. When using third-party models via Amazon Bedrock, the model provider also does not have access to customer data for training their base models. This is a fundamental data privacy commitment from AWS. Therefore, no additional action is required; the correct understanding is that AWS and its model providers do not use customer data for training. Enabling an opt-out setting is not necessary because the default is already no training on customer data.

Answer

Disable all logging

Answer

Enable the 'Opt-out' setting in the Bedrock console

Answer

Encrypt all data with a customer-managed key

Question 13

Which service should be used to provide secure identity and access management for an application accessing Bedrock?

Accepted Answer

AWS IAM. AWS IAM is the correct service for providing secure identity and access management for applications accessing Amazon Bedrock. IAM roles and policies define precisely which Bedrock actions (such as InvokeModel, RetrieveAndGenerate) an application or user can perform, and IAM roles can be assumed by compute resources like Lambda functions or EC2 instances to obtain temporary credentials. This is the foundational AWS access control mechanism that Bedrock integrates with natively for authorization.

Answer

AWS Secrets Manager

Answer

AWS Directory Service

Answer

Amazon Cognito

Question 14

When fine-tuning a model on Amazon Bedrock, which THREE security considerations are critical?

Accepted Answer

Limiting IAM permissions for the fine-tuning job. Option B is correct because fine-tuning jobs on Amazon Bedrock should run under a scoped IAM role/service role that grants only the permissions needed (e.g., s3:GetObject on the specific training bucket and bedrock:CreateModelCustomizationJob), following least privilege to limit blast radius. Option C is correct because training data stored in Amazon S3 should be encrypted at rest with AWS KMS (SSE-KMS), and Bedrock requires access to the KMS key to read the dataset, protecting sensitive training content. Option E is correct because datasets used for fine-tuning must be reviewed and scrubbed of personally identifiable information (PII) to avoid embedding sensitive data into model weights and to comply with privacy regulations. Option A is wrong because using the root user violates AWS best practices; root should not be used for workloads and lacks granular, auditable permissions. Option D is wrong because making the training dataset publicly readable exposes proprietary or sensitive data to anyone and is a severe security misconfiguration.

Answer

Using a root user account to launch the training job

Answer

Making the training dataset publicly readable

Question 15

Your organization wants to evaluate the quality and safety of model outputs using a formal testing framework. Which service is designed for this?

Accepted Answer

Amazon Bedrock Model Evaluation. Amazon Bedrock Model Evaluation is purpose-built to assess foundation model outputs for quality, accuracy, robustness, and safety (including toxicity and bias) using either automatic metrics or human/LLM-as-judge workflows. It is the only service in the list designed specifically for evaluating generative AI model outputs.

Answer

AWS CloudWatch Synthetics

Answer

Amazon SageMaker Pipelines

Answer

AWS CodePipeline