Machine learning (ML) administrators play a critical role in maintaining the security and integrity of ML workloads. Their primary focus is to ensure that users operate with the utmost security, adhering to the principle of least privilege. However, accommodating the diverse needs of different user personas and creating appropriate permission policies can sometimes impede agility. To address this challenge, AWS introduced Amazon SageMaker Role Manager in December 2022. SageMaker Role Manager is a powerful tool can you can use to swiftly develop persona-based roles, which can be easily customized to meet specific requirements.
With SageMaker Role Manager, administrators can efficiently define persona-based roles tailored to distinct user groups. This approach ensures that individuals have access only to the resources and actions essential for their tasks, reducing the risk of unauthorized actions or breaches. SageMaker Role Manager also allows for fine-grained customization. ML administrators can tailor the roles to meet specific requirements by modifying the permissions associated with each persona. This flexibility ensures that the permissions align precisely with the tasks and responsibilities of individual users, providing a robust security framework while accommodating unique use cases.
SageMaker Role Manager is currently available on the Amazon SageMaker console of all commercial Regions. Today, we are launching the ability to define customized permissions in minutes with SageMaker Role Manager via the AWS Cloud Development Kit (AWS CDK). This addresses a critical obstacle to wider adoption because ML administrators can now automate their tasks programmatically. With the power of the AWS CDK, ML administrators can streamline workflows, reduce manual efforts, and ensure consistency in managing permissions for their ML infrastructure.
Solution overview
With the release of the SageMaker Role Manager CDK, we are launching two new infrastructure as code (IaC) capabilities:
Create fine-grained permissions for ML personas
Create fine-grained permissions for automated jobs through Amazon SageMaker Pipelines, AWS Lambda, and other AWS services
You can create fine-grained AWS Identity and Access Management (IAM) roles for ML personas such as data scientist, ML engineer, or data engineer. SageMaker Role Manager offers predefined personas and ML activities combined to streamline your permission generation process, allowing your ML practitioners to perform their responsibilities with the least privilege permissions. For secure access to your ML resources, SageMaker Role Manager allows you to specify networking and encryption permissions for Amazon Virtual Private Cloud (Amazon VPC) resources and AWS Key Management Service (AWS KMS) encryption keys. Furthermore, you can customize permissions by attaching your own customer managed policies.
The SageMaker Role Manager CDK lets you define custom permissions for SageMaker users in minutes. It comes with a set of predefined policy templates for different personas and ML activities. Personas represent the different types of users that need permissions to perform ML activities in SageMaker, such as data scientists or MLOps engineers. ML activities are a set of permissions to accomplish a common ML task, such as running Amazon SageMaker Studio applications or managing experiments, models, or pipelines. After you have selected the persona type and the set of ML activities, the SageMaker Role Manager CDK automatically creates the required IAM role and policies that you can assign to SageMaker users. Similarly, you can also create IAM roles with fine-grained permissions for automated jobs such as running SageMaker Pipelines.
Prerequisites
To start using the SageMaker Role Manager CDK, you need to complete the following prerequisite steps:
Set up a role for your ML administrator to create and manage personas, as well as the IAM permissions for those users. For a sample admin policy, refer to the prerequisite section in Define customized permissions in minutes with Amazon SageMaker Role Manager blog post.
Create a compute-only persona role (if you don’t have any) for passing to jobs and endpoints. For instructions to set up that role, refer to Using the role manager.
Set up your AWS CDK development environment. For instructions, refer to Getting started with the AWS CDK.
Install and run the SageMaker Role Manager CDK
Complete the following steps to set up the SageMaker Role Manager CDK:
Create your AWS CDK app and give it a name; for example, RoleManager.
Navigate to the RoleManager folder and run the following command to create a blank typescript AWS CDK project:
cdk init app –language typescript
Open package.json and add the highlighted package as shown in the following code:
“dependencies”: {
“aws-cdk-lib”: “2.85.0”,
“@cdklabs/cdk-aws-sagemaker-role-manager”: “0.0.15”,
“constructs”: “^10.0.0”,
“source-map-support”: “^0.5.21”
}
Run the following command to install the new cdk-aws-sagemaker-role-manager package:
npm install
Navigate to the lib folder and replace role_manager_stack.ts with the following code:
import * as cdk from ‘aws-cdk-lib’;
import { Construct } from ‘constructs’;
import * as iam from ‘aws-cdk-lib/aws-iam’;
import { Activity } from ‘@cdklabs/cdk-aws-sagemaker-role-manager’;
export class RoleManagerStack extends cdk.Stack {
constructor(scope: Construct, id: string, props?: cdk.StackProps) {
super(scope, id, props);
const activity = Activity.manageJobs(this, ‘id1’, {
rolesToPass: [iam.Role.fromRoleName(this, ‘passRoleId’, ‘passRoleName’)],
});
activity.createRole(this, ‘newRoleId’, ‘newRoleName’, newRoleDescription’);
}
}
Replace passRoleId, passRoleName, newRoleId, newRoleName, and newRoleDescription based on your requirements for role creation.
Navigate back to your AWS CDK app home folder and run the following command to verify the generated AWS CloudFormation template:
cdk synth
Finally, run the following command to run the CloudFormation stack in your AWS account:
cdk deploy
You should see an AWS CDK deployment output similar to the one in the following screenshot.
More SageMaker Role Manager CDK examples are available in the following GitHub repo.
ML persona and activity CDK reference
Administrators can define ML activities using one of the ML activity static functions of the ML activity class. For a list of the latest versions, refer to ML activity reference.
The ML persona class supports the following methods:
customizeVPC(subnets, securityGroups) – Customizes the VPC of all activities that support VPC customization of personas.
customizeKMS(dataKeys, volumeKeys) – Customizes KMS keys of all activities that support KMS key customization of personas.
createRole(scope, id, roleNameSuffix, roleDescription) – Creates a role with the persona’s activities’ permissions similar to the UI in the scope with ID, with the name SageMaker-${roleNameSuffix} and optionally with the passed role description.
grantPermissionsTo(identity) – Grants the persona’s activities’ permissions to the identity. The passed identity can be a role or an AWS resource associated with a role (for example, a Lambda function with the role of the Lambda function describing which resources the Lambda function can access).
grantPermissionsTo() – Updates the role of the passed identity to have the permissions specified in the ML activity.
The ML activity class supports the same set of functions as ML personas; however, the difference is an ML activity is constrained to a single activity when using this interface to create IAM roles.
Conclusion
SageMaker Role Manager enables you to create customized roles based on personas, pre-built ML activities, and custom policies, significantly reducing the time required. Now, with this latest AWS CDK support, the ability to define roles is further expanded to support infrastructure as code. This empowers ML practitioners to work programmatically in SageMaker, enhancing efficiency and enabling seamless integration into their workflows.
We would like to hear from you on how this new feature is helping you. Try out the new AWS CDK support for SageMaker Role Manager and send us your feedback!
To learn more about how to use SageMaker Role Manager, refer to the SageMaker Role Manager Developer Guide.
About The Authors
Akash Bhatia is a Principal Solution Architect with experience spanning multiple industries, including Manufacturing, Automotive, Retail ,and Space and Technology. Currently working in Amazon Web Services Enterprise Segments, Akash works closely with a diverse range of clients, including Fortune 100 companies and start-ups, to facilitate their cloud migration journey. In addition to his technical expertise, Akash has led product and program management, having successfully overseen numerous large-scale initiatives throughout his career.
Ram Vittal is a Principal ML Solutions Architect at AWS. He has over 20 years of experience architecting and building distributed, hybrid, and cloud applications. He is passionate about building secure and scalable AI/ML and big data solutions to help enterprise customers with their cloud adoption and optimization journey to improve their business outcomes. In his spare time, he enjoys riding motorcycle, playing tennis, and photography.
Ozan Eken is a Senior Product Manager at Amazon Web Services. He has over 15 years of experience in consulting and product management. He is passionate about building governance products, and Admin capabilities in Machine Learning for enterprise customers. Outside of work, he likes exploring different outdoor activities and watching soccer.