Detection vs De-identification
Guardian Layer separates privacy workflows into two related steps:
- Detection finds sensitive content.
- De-identification changes that content to produce safer output.
Most applications can go directly to de-identification. Use detection first when you need to inspect, review, or control what will be changed.
Detection
Detection identifies sensitive terms and returns metadata. It does not change the input text.
Use detection when you need to:
- Review what Guardian Layer found before changing the text.
- Build a human review UI.
- Audit sensitive terms without creating a de-identified copy.
- Decide whether a document or message needs de-identification.
Endpoint:
POST /api/v1/analyze/text/proprietary
Example request:
{
"text": "The Meridian account is managed by Dana Reyes.",
"domain": "General",
"pca_dimension": 2
}
Response fields include:
| Field | Meaning |
|---|---|
tokens | Tokens recognized in the proprietary vocabulary. |
sensitive_words | Sensitive terms detected in the input. |
words_in_hull | Related terms found by semantic analysis. |
suggestions | Candidate replacements for detected terms. |
pca_dimension | The PCA dimension used for the analysis. |
De-identification
De-identification creates a safer output by changing detected sensitive values.
Use de-identification when you need to:
- Send safer text to an LLM.
- Share de-identified content with another system.
- Generate privacy-preserving sample data.
- Prepare content for downstream processing.
For Guardian Layer text de-identification, use:
POST /api/v1/deidentify/text/proprietary/outputs
Set masking_type based on the output style you want:
masking_type | Behavior |
|---|---|
transform | Replaces sensitive values with readable alternatives. |
redact | Replaces sensitive values with masking marks. |
For detailed request and response examples, see Transform (Proprietary) and Redact / Masking / Placeholder.
Choosing a Workflow
| Goal | Recommended workflow |
|---|---|
| See what Guardian Layer would detect | Use detection. |
| Produce de-identified text immediately | Use de-identification. |
| Let a human approve changes first | Detect first, then de-identify after review. |
| Produce readable de-identified text | Use masking_type: "transform". |
| Hide sensitive values more visibly | Use masking_type: "redact". |