Data Leakage Prevention

Data Leakage Prevention (DLP) identifies and protects sensitive data like personally identifiable information (PII), credentials, and proprietary content.

The Risk

LLMs can leak sensitive data in two ways:

1. Training Data Leakage

Models may memorize and regurgitate sensitive data from their training set.

2. Context Leakage

When processing documents or conversation history, models may expose sensitive information in their responses.

Glitch DLP detects sensitive data in both inputs (preventing submission) and outputs (preventing exposure).

PII Categories

Detector Type	Description	Example
`pii/email`	Email addresses	user@example.com
`pii/credit_card`	Credit/debit card numbers	4111-1111-1111-1111
`pii/ssn`	Social Security Numbers	123-45-6789
`pii/phone`	Phone numbers	+1 (555) 123-4567
`pii/address`	Physical addresses	123 Main St, City, ST 12345
`pii/name`	Personal names	John Smith

Configuration

Basic PII Protection

{
  "output_detectors": [
    { "detector_type": "pii/email", "threshold": "L2", "action": "block" },
    { "detector_type": "pii/credit_card", "threshold": "L1", "action": "block" },
    { "detector_type": "pii/ssn", "threshold": "L1", "action": "block" }
  ]
}

Full DLP Policy

{
  "input_detectors": [
    { "detector_type": "pii/credit_card", "threshold": "L1", "action": "block" },
    { "detector_type": "pii/ssn", "threshold": "L1", "action": "block" }
  ],
  "output_detectors": [
    { "detector_type": "pii/email", "threshold": "L2", "action": "block" },
    { "detector_type": "pii/credit_card", "threshold": "L1", "action": "block" },
    { "detector_type": "pii/ssn", "threshold": "L1", "action": "block" },
    { "detector_type": "pii/phone", "threshold": "L2", "action": "flag" },
    { "detector_type": "pii/address", "threshold": "L3", "action": "flag" }
  ]
}

Detection Examples

Output: "Your card ending in 4532-8901-2345-6789 has been charged."

Detection: pii/credit_card
Confidence: 0.98
Action: BLOCKED

Note: Credit card patterns have high confidence due to
Luhn checksum validation.

Output: "Contact john.doe@company.com for support."

Detection: pii/email
Confidence: 0.95
Action: BLOCKED

Output: "SSN: 123-45-6789"

Detection: pii/ssn
Confidence: 0.97
Action: BLOCKED

Output: "Call us at +1 (555) 123-4567"

Detection: pii/phone
Confidence: 0.85
Action: FLAGGED (if configured)

Threshold Recommendations

Detector	Recommended Level	Notes
`pii/credit_card`	L1	High-precision pattern with checksum
`pii/ssn`	L1	Strict pattern, low false positives
`pii/email`	L2	Email-like patterns can be benign
`pii/phone`	L2-L3	Many number patterns look like phones
`pii/address`	L3	Addresses have high variance
`pii/name`	L3-L4	Names are highly contextual

Input vs. Output Protection

Input Protection

Prevents users from submitting sensitive data:

{
  "input_detectors": [
    { "detector_type": "pii/credit_card", "threshold": "L1", "action": "block" }
  ]
}

Use cases:

Prevent accidental PII submission
Compliance with data handling policies
Reduce liability from processing sensitive data

Output Protection

Catches sensitive data in LLM responses:

{
  "output_detectors": [
    { "detector_type": "pii/credit_card", "threshold": "L1", "action": "block" },
    { "detector_type": "pii/email", "threshold": "L2", "action": "block" }
  ]
}

Use cases:

Prevent training data leakage
Protect against prompt injection data extraction
Compliance with privacy regulations (GDPR, CCPA)

Allow Lists for Known Data

Sometimes legitimate data looks like PII. Use allow lists:

{
  "allow_list": {
    "entries": [
      "support@yourcompany.com",
      "sales@yourcompany.com"
    ],
    "match_type": "exact"
  },
  "output_detectors": [
    { "detector_type": "pii/email", "threshold": "L2", "action": "block" }
  ]
}

This blocks email addresses except your company’s support emails.

Actions and Responses

Blocked Response

HTTP/1.1 403 Forbidden
X-Risk-Blocked: true
X-Risk-Categories: pii/credit_card
X-Risk-Confidence: 0.98

{
  "error": {
    "message": "Response blocked: sensitive data detected",
    "type": "data_leakage_prevention",
    "code": "pii_detected"
  }
}

Flagged Response

HTTP/1.1 200 OK
X-Risk-Blocked: false
X-Risk-Categories: pii/email
X-Risk-Confidence: 0.85

Content is delivered but flagged for logging/review.

Best Practices

1. Always Protect High-Sensitivity Data

Credit cards and SSNs should always be blocked:

{
  "output_detectors": [
    { "detector_type": "pii/credit_card", "threshold": "L1", "action": "block" },
    { "detector_type": "pii/ssn", "threshold": "L1", "action": "block" }
  ]
}

2. Flag Before Blocking (Low-Confidence)

For lower-confidence detections, start with flagging:

{
  "output_detectors": [
    { "detector_type": "pii/name", "threshold": "L3", "action": "flag" }
  ]
}

Review flagged content to tune your policy.

3. Combine with Custom Detectors

Add patterns for domain-specific sensitive data:

{
  "custom_detectors": [
    {
      "name": "employee_id",
      "pattern": "EMP-\\d{6}",
      "action": "block",
      "description": "Internal employee IDs"
    }
  ]
}

Compliance Considerations

DLP helps with:

Regulation	Relevant Data Types
GDPR	All PII (names, emails, addresses)
CCPA	California resident PII
PCI-DSS	Credit card numbers
HIPAA	Health information (custom detectors)

Next Steps

Allow & Deny Lists — Customize detection rules
Custom Detectors — Add domain-specific patterns
Malicious Links — Protect against harmful URLs