This Quick Start deployment of Amazon SageMaker adds guardrails so you can build, train, and deploy machine learning (ML) models in a more secure environment. Guardrails are high-level rules that provide ongoing governance for your overall AWS environment. AWS provides additional security by using AWS PrivateLink, Amazon CloudWatch, AWS Identity and Access Management (IAM), AWS Key Management Service (AWS KMS), and other native services.

Guardrails deploy within an AWS-managed virtual private cloud (VPC) and elastic network interfaces to provide security mechanisms and add-on features that are not provided with native SageMaker. They also provide more secure access to AWS services with VPC endpoint interfaces and Amazon Amazon Simple Storage Service (Amazon S3) bucket gateways within your own VPC.

https://aws.amazon.com/quickstart/architecture/amazon-sagemaker-with-guardrails/