Courseiva
Question 119 of 835
hardMultiple ChoiceObjective-mapped

Encrypting SageMaker Model Artifacts at Rest with KMS

An ML team trained a model using SageMaker and stored the model artifacts in S3 with server-side encryption using AWS KMS (SSE-KMS). They need to deploy the model to a SageMaker endpoint that uses a different KMS key for inference data encryption. What must they do to ensure the endpoint can decrypt the model artifacts?

Quick Answer

The answer is to grant the SageMaker execution role access to both KMS keys. This is required because the execution role acts as the intermediary between the S3 bucket containing the model artifacts and the SageMaker endpoint; it must have `kms:Decrypt` permission on the key that encrypted the artifacts at rest, and also `kms:Encrypt` and `kms:Decrypt` on the separate key used for inference data encryption. On the AWS Certified Machine Learning Engineer Associate MLA-C01 exam, this scenario tests your understanding of how SageMaker decouples storage encryption from inference encryption, and a common trap is assuming both must use the same key. Instead, the role simply needs explicit permissions for each key’s operation. Remember the memory tip: "Two keys, one role—decrypt the model, encrypt the goal."

⚠ Common exam trap

Test-takers frequently assume the same key must be used for both operations or that identical key material makes keys interchangeable, but AWS KMS treats each key as a separate resource with distinct ARNs and policies, requiring explicit permissions for each.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

Grant the SageMaker execution role access to both KMS keys.

The SageMaker endpoint needs to decrypt the model artifacts stored with SSE-KMS using the original KMS key, and then re-encrypt the inference data with a different KMS key. The SageMaker execution role must have kms:Decrypt permission on the key used for the model artifacts and kms:Encrypt permission on the key used for inference data encryption. Without granting access to both keys, the endpoint cannot read the model artifacts or encrypt the output.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Provide the same KMS key for both model artifacts and inference data.

    Why it's wrong here

    Using the same key is an option but not required; different keys can be used with proper permissions.

  • Use a customer-managed key (CMK) with the same key material.

    Why it's wrong here

    Key material is irrelevant; permissions are key.

  • Grant the SageMaker execution role access to both KMS keys.

    Why this is correct

    The role needs decrypt on the artifact key and encrypt/decrypt on the inference key.

  • Configure the endpoint to use SSE-S3 instead of SSE-KMS.

    Why it's wrong here

    Changing encryption type would require re-uploading artifacts.

Quick reference

AWS S3 Storage Class Comparison

Storage ClassMin DurationRetrievalUse Case
S3 StandardNoneImmediateFrequently accessed data
S3 Standard-IA30 daysImmediateInfrequent access, rapid retrieval
S3 One Zone-IA30 daysImmediateNon-critical infrequent data
S3 Intelligent-TieringNoneImmediate–hoursUnknown or changing access patterns
S3 Glacier Instant90 daysMillisecondsArchive with instant retrieval
S3 Glacier Flexible90 daysMinutes–hoursArchive, flexible retrieval
S3 Glacier Deep Archive180 daysHoursLong-term compliance archive

About these practice questions

Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

Same concept, more angles

1 more way this is tested on MLA-C01

These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.

Variation 1. A machine learning engineer wants to encrypt model artifacts stored in Amazon S3. The artifacts are created and used by SageMaker training jobs and endpoints. What is the simplest way to ensure encryption at rest?

easy
  • A.Create an S3 bucket with default encryption using SSE-S3 and allow SageMaker access.
  • B.Use SageMaker's default encryption with an AWS managed key.
  • C.Enable S3 bucket versioning and MFA delete.
  • D.Use a custom KMS key and grant SageMaker permission to use it.

Why A: SSE-S3 provides server-side encryption with Amazon S3-managed keys, which is the simplest way to encrypt data at rest because it requires no additional key management or configuration beyond enabling default encryption on the bucket. SageMaker training jobs and endpoints can seamlessly read and write encrypted objects when the bucket has default SSE-S3 enabled, as SageMaker automatically handles the decryption during access. This approach minimizes operational overhead while meeting the encryption-at-rest requirement.

Last reviewed: Jul 4, 2026

Question Discussion

Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.

Loading comments…

Sign in to join the discussion.

This MLA-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MLA-C01 exam.