> ## Documentation Index
> Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt
> Use this file to discover all available pages before exploring further.

# PII Redaction

> Learn how to implement PII redaction in your AI applications using TrueFoundry's integration options with AWS Bedrock, Azure PII, and open-source tools.

PII (Personally Identifiable Information) redaction refers to the process of masking, removing, or replacing sensitive personal information within a text or data source to prevent the exposure of data that can be used to identify an individual.

#### Why is PII redaction important?

* **Data privacy and security:** Redacting PII ensures that sensitive information is not exposed, helping organizations comply with regulations such as GDPR and CCPA.
* **Risk mitigation:** Masking or removing PII reduces the risk of data breaches and unauthorized access to personal information.
* **Compliance:** Many regulations require organizations to not only detect but also redact or anonymize PII before storing, processing, or sharing data.

#### Truefoundry's PII redaction solutions

* [AWS Bedrock Guardrails](https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html)\
  You can use the Bedrock integration on Truefoundry to achieve PII redaction. A brief tutorial for setting this up is provided at the end of this page.

* [Azure PII](https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/overview?tabs=text-pii)\
  You can use the Azure PII integration on Truefoundry to achieve PII redaction. It is a built-in guardrail integration that can be used to redact PII from the input and output of the model.

* [Open-source Presidio](https://github.com/microsoft/presidio)\
  You can also implement PII redaction using the custom guardrail integration option on Truefoundry Gateway. As a starting point, refer to the Truefoundry Guardrail Template Repository, which already includes PII redaction using Presidio. This template can be extended to suit your specific requirements.

* [Guardrails.io](https://hub.guardrailsai.com/validator/guardrails/detect_pii)\
  Similarly, Guardrails.io functionality can be achieved by building a custom guardrail using the same template repository. The template provides a foundation for integrating additional PII detection or redaction logic as needed.

<Note>
  Link to the [Truefoundry Guardrail Template Repository](https://github.com/truefoundry/custom-guardrails-template)
</Note>

### How to setup PII redaction using Bedrock Guardrails on Truefoundry?

<iframe href="https://app.supademo.com/embed/cmd4ali554fj5c4kjsld60lyz" typeofembed="iframe" height="475px" width="100%" provider="app.supademo.com" src="https://app.supademo.com/embed/cmd4ali554fj5c4kjsld60lyz" style={{ border: "none", display: "flex", margin: "auto" }} title="PII Redaction with Bedrock Guardrails Demo" alt="Interactive demo showing how to set up PII redaction using AWS Bedrock Guardrails on TrueFoundry" />

* Create guardrail on Bedrock, with sensitive information filter with Input & Ouput action as `Mask`
  <Frame>
    <img src="https://mintcdn.com/truefoundry/iMid4yIOHvzf4Z4V/images/pii-redaction-1.jpeg?fit=max&auto=format&n=iMid4yIOHvzf4Z4V&q=85&s=fe81f7d9ae689bddced2c50a6fb2e3b0" alt="AWS Bedrock console showing the sensitive information filter configuration with masking option selected" width="1280" height="612" data-path="images/pii-redaction-1.jpeg" />
  </Frame>
* Create a new or Add to an existing guardrail group on Truefoundry Gateway **(AI Gateway -> Guardrails -> Add New Guardrail Group or Add/Edit Guardrails)**
* Add bedrock guardrail and fill the details such as:
  * Name
  * GuardrailID
  * Version
  * Region
  * Auth Data (AWS Access Key ID and Secret Access Key or ARN Based Credentials)
* Create a new or Edit existing guardrail configuration on Truefoundry Gateway **(AI Gateway -> Config -> Guardrail -> Create/Edit)**
* Test out the guardrail in playground **(AI Gateway -> Playground)**