Home icon
Detect and redact personally identifiable information using Amazon Bedrock Data Automation and Guardrails

Machine Learning Blog



This article demonstrates an automated PII detection and redaction solution using Amazon Bedrock Data Automation and Guardrails for processing emails and attachments at scale.

  • Detects and redacts PII (SSNs, driver's licenses, phone numbers) from email content and attachments
  • Unified approach handles both text and image content consistently across workflows
  • Solution uses Lambda, EventBridge, S3, DynamoDB, and Bedrock services for orchestration
  • Optional React-based web portal allows authorized users to manage redacted communications
  • Includes complete deployment guide with three CloudFormation stacks (S3, Consumer, Portal)
  • Supports Amazon SES for incoming email handling or direct S3 bucket uploads
  • Provides audit trails, encryption, and access controls for compliance requirements
  • Scalable architecture processes high volumes of incoming emails automatically

The solution provides organizations with an enterprise-scale framework for automating PII protection across diverse communication channels while maintaining compliance and operational efficiency.



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.