OpenAI privacy-filter for PII detection and masking is now available in Amazon SageMaker JumpStart

Amazon SageMaker JumpStart Privacy-Filter Availability

AWS has introduced a privacy-filter in Amazon SageMaker JumpStart, enhancing the range of foundation models available to customers. This model, developed by OpenAI, is a bidirectional token-classification model for detecting and masking personally identifiable information (PII) in text, facilitating data sanitization workflows on AWS infrastructure.

The privacy-filter is designed for high-throughput data sanitization, offering speed, context-awareness, and tunability. It identifies and labels PII categories such as account numbers, addresses, emails, names, phone numbers, URLs, dates, and secrets in a single forward pass.

What to do

• Deploy the model via SageMaker Studio's Models section or the SageMaker Python SDK.
• Utilize the model for specific AI use cases.

For further details on deploying and using foundation models in SageMaker JumpStart, refer to the Amazon SageMaker JumpStart documentation.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.