AWS Machine Learning Blog

AWS CloudTrail integration is now available in Amazon SageMaker

AWS customers have been requesting a way to log activity in Amazon SageMaker, to help you meet your governance and compliance needs. I’m happy to announce that Amazon SageMaker is now integrated with AWS CloudTrail, a service that enables you to log, continuously monitor, and retain account information related to Amazon SageMaker API activity. Amazon SageMaker API calls, whether through the Amazon SageMaker SDK, AWS SDK, Apache Spark SDK for Amazon SageMaker, or Amazon SageMaker console, are captured and delivered to an Amazon S3 bucket to provide an event history of your AWS account activity. The recorded information includes the source IP address, the date and time the request was made, the user identity associated with the request, and the parameters requested.

The integration with AWS CloudTrail adds to the set of controls that are in place as part of our continued commitment to our shared security and compliance responsibilities. This builds on the controls we delivered last month to meet ISO standard certification. This serves as a foundation for future governance-focused, audit-friendly features in Amazon SageMaker to help customers establish and operate a secure and compliant machine learning (ML) platform.

For more information, see the Amazon SageMaker documentation.

Additional Reading

About the Author

Kumar Venkateswar is a Product Manager in the AWS ML Platforms team, which includes Amazon SageMaker, Amazon Machine Learning, and the AWS Deep Learning AMI. When not working, Kumar plays the violin and Magic: the Gathering.