Philter redacts, masks, and encrypts PII and PHI through its powerful API.  


Philter is an advanced tool for deidentification and redacting PII and PHI from text.

Using state of the art natural language processing, Philter accomplishes deidentification by analyzing text and PDF documents for sensitive information to redact, mask, encrypt, hash, or replace with random values. You can apply conditional logic based on attributes such as the type or content of sensitive information to have fine-grained control over how sensitive information is identified and manipulated and to generate alerts.

Some of the types of information Philter can identify include: Ages, Bitcoin Addresses, Cities, Counties, Credit Cards, Custom Dictionaries, Custom Identifiers (such as medical record numbers, financial transaction numbers), Dates, Drivers License Numbers, Email Addresses, IBAN Codes, IP Addresses, MAC Addresses, Passport Numbers, Persons Names, Phone and Fax Numbers, Physician Names, SSNs and TINs, Shipping Tracking Numbers, States, URLs, US street addresses, VINs, Zip Codes

Contact us for a complementary demonstration and exploration engagement or run Philter as a container on in the cloud today.

State of the art NLP technologies

Mask, Redact, Encrypt, Randomize

Deidentify unstructured, free text documents

Supports PDF documents

Running Philter

docker run -it -p 8080:8080

See all available tags.

Example Redacted Document

In the images below, the public domain legal PDF document was provided to Philter for redaction. Philter was configured to redact person’s names, dates, and an identifier matching the case number. Philter can be customized to match virtually any redaction needs.

Original document:

Philter redacted document: