AI engineering glossary · Evals guardrails AI security
What is PII redaction?
PII redaction (also called PII masking): Removing or replacing personal information in text with placeholders, such as [PHONE] or [NAME], so that the remaining content can be stored, analysed or sent to a model with less privacy risk. Some systems map placeholders back after processing.
PII redaction: an example
A support transcript reading 'Call Rohan at 98xxxxxx10' becomes 'Call [NAME] at [PHONE]' before being used for evaluation.
Related terms
More Evals guardrails AI security terms
- Prompt injection
- Prompt leaking
- promptfoo
- PyRIT
- Red teaming
- Reference-based evaluation
- Reference-free evaluation
- Refusal rate
Where you learn it
PII redaction is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.