PII Detection

Scans for personally identifiable information

API Field: pii_enabled

Overview

PII (Personally Identifiable Information) Detection identifies sensitive personal data that could be used to identify, contact, or locate an individual. This scanner helps organizations maintain data privacy compliance and prevent accidental exposure of sensitive information through AI interactions.

What It Detects

Social Security Numbers (SSN)
Email addresses
Phone numbers (various formats)
Credit card numbers
Physical addresses
Date of birth
Driver's license numbers
Passport numbers
Bank account numbers

Why It Matters

Handling PII incorrectly can result in identity theft, privacy violations, regulatory fines (GDPR, CCPA), and loss of customer trust. AI systems must not inadvertently store, process, or expose PII.

Technical Details

Risk Score Range

0.0 - 1.0 (High risk: > 0.5)

Confidence Level

Typically 0.90 - 0.99

Processing Time

< 50ms per scan

Common Use Cases

Customer support automationHealthcare AI applicationsFinancial services chatbotsHR and recruitment toolsLegal document analysis

Detection Examples

Threat Example #1Risk: 98%

My social security number is 123-45-6789, can you remember it?

Explicit SSN disclosure - high-risk PII that requires immediate protection.

Threat Example #2Risk: 85%

Please send the invoice to john.smith@company.com at 123 Main Street, New York

Multiple PII elements: email address and physical address.

Threat Example #3Risk: 99%

My credit card is 4111-1111-1111-1111 expiring 12/25

Payment card information - requires PCI DSS compliance.

API Usage

Enable this scanner in your API request by setting pii_enabled to true in your API key settings, or include it in your request:

curl -X POST https://benguard.io/api/v1/scan \
  -H "X-API-Key: ben_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Your user input here"
  }'

The scanner settings are configured per API key in your dashboard under Settings → Scanner Configuration.

Response Format

When this scanner detects a threat, the response will include:

{
  "is_valid": false,
  "status": "threat_detected",
  "risk_score": 0.98,
  "threat_types": ["pii"],
  "details": {
    "results": [
      {
        "scanner": "pii",
        "threat_detected": true,
        "risk_score": 0.98,
        "confidence": 0.92,
        "details": {
          "reason": "Explicit SSN disclosure - high-risk PII that requires immediate protection.",
          "evidence": ["detected pattern in input"]
        }
      }
    ]
  },
  "request_id": "req_abc123"
}

Best Practices

Never store PII in conversation logs without encryption
Implement automatic PII redaction in responses
Use tokenization for necessary PII processing
Establish clear data retention policies
Train models to avoid requesting unnecessary PII

Related Scanners

Consider enabling these related scanners for comprehensive protection:

HIPAA Compliance

Scans for Protected Health Information (PHI)

GDPR/CCPA Compliance

Detects EU/California protected personal data

LGPD Compliance

Scans for Brazilian personal data (CPF, RG, etc.)