PII detection
PII detection is the identification of information in data or content that can identify a specific person.
Machine Learning Platform Engineering
Personally identifiable information detection is the identification of information that can identify an individual in text or other content.
- How it is used
- Screens user inputs before expensive LLM processing to prevent sensitive information from entering the pipeline.
- How deep it goes
- Implements entity selection, validator composition, failure actions, validation calls, and exception handling.
- Examples
- Uses email addresses, credit-card numbers, and Social Security numbers, including automatic email redaction.
- What you can do after
- Apply it via Guardrails AI to validate and sanitize user inputs before LLM processing.
Read how Machine Learning Platform Engineering explains PII detection →
Building Reliable AI Systems
The process of identifying information in data or outputs that can identify a specific person.
- How it is used
- Protects personal information as the privacy layer in a defense-in-depth responsible AI system.
- How deep it goes
- Recommends pipeline detection and redaction but does not specify detectors, implementation, or accuracy evaluation.
- What you can do after
- Understand its role in privacy pipelines and pair detection with redaction, data minimization, and regulatory compliance.
Read how Building Reliable AI Systems explains PII detection →
Related concepts
- output guardused by · An output guard is a post-processing component that checks, transforms, blocks, or routes generated responses before delivery.
- privacyaddresses · Privacy is the protection and controlled handling of information or activities to prevent inappropriate access, collection, use, or disclosure.
- detectionkind of · Detection is the process of identifying whether a specified condition, abnormality, failure, or undesirable behavior is present or suspected.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.