PII Detection

This guardrail detects and handles personally identifiable information like emails, SSNs, names, etc.

​

Options:

entity_types: An array of PII types to detect, e.g., [“email”, “ssn”, “name”, “address”]
The following entity types are supported:

• email
• phone
• ssn
• credit_card
• address
• name
• date_of_birth
• ip_address
• passport
• drivers_license
• crypto
• iban
• nrp
• medical_license
• url
• us_bank_number
• us_itin
• uk_nhs
• uk_nino
• es_nif
• es_nie
• it_fiscal_code
• it_driver_license
• it_vat_code
• it_passport
• it_identity_card
• pl_pesel
• sg_nric_fin
• sg_uen
• au_abn
• au_acn
• au_tfn
• au_medicare
• in_pan
• in_aadhaar
• in_vehicle_registration
• in_voter
• in_passport
• fi_personal_identity_code

​

Example

name: communication-guardrails
type: gateway-guardrails-config
rules:
  - id: privacy-filter
    when:
      models:
        - openai-main/gpt-3-5-turbo
      subjects:
        - user:example@company.com
    input_guardrails:
      - type: pii
        action: transform
        options:
          entity_types:
            - email
            - phone
            - ssn
            - name
    output_guardrails:
      - type: pii
        action: transform
        options:
          entity_types:
            - email
            - phone
            - ssn
            - name
guardrails_service_url: https://example-guardrails-service.company.com

In this example, the guardrail system automatically detects and anonymizes emails, phone numbers, social security numbers, and names in both the incoming and outgoing data streams. This process helps maintain the privacy of individuals while allowing the company to handle sensitive data securely and compliantly.