: About Custom Document Types
Focus
Focus

About Custom Document Types

Table of Contents

About Custom Document Types

Learn more about how
Enterprise Data Loss Prevention (E-DLP)
uses custom documents you upload to prevent exfiltration of sensitive data.
Where Can I Use This?
What Do I Need?
  • Strata Cloud Manager
  • Enterprise Data Loss Prevention (E-DLP)
    license
  • (
    SaaS Security
    only
    )
    SaaS Security
    license
  • Prisma Access
    license
  • AIOps for NGFW Premium
    license
  • AIOps for NGFW Free
    license
Enterprise Data Loss Prevention (E-DLP)
supports upload and detection of custom documents containing intellectual property for which you want to prevent exfiltration. You can upload a custom document type to
Enterprise DLP
to classify and detect standardized documents and prevent exfiltration of sensitive data. Custom document types uploaded to
Enterprise DLP
are used in data profiles as match criteria and can be used along with predefined Machine Learning-based data patterns to apply additional ML-based detection algorithms complimented by confidential or sensitive data specific to your organization.
Enterprise DLP
uses Indexed Document Matching and Vector Machine Learning to fingerprint and index uploaded custom documents to scan for and detect documents that completely or partially match what you have already uploaded.
  • Indexed Document Matching (IDM)
    —Used to fingerprint documents and create a document type for documents commonly used by your organization. Uploading multiple documents allows you to create a custom document repository that you can use in a data profile.
  • Vector Machine Learning (VML)
    —Supervised machine learning model that analyzes document types for classifications. As you upload more custom documents as types,
    Enterprise DLP
    is able to continuously train the VML model to accurately detect sensitive data matches to inspect for and prevent exfiltration (Positive Training Documents) and those to ignore (Negative Training Set).
Using IDM for detection of sensitive data is powerful enables
Enterprise DLP
to continuously improve its detection capabilities by indexing unstructured text in your documents. Examples of different types of custom documents where IDM can be successfully applied are:
  • Standardized forms or documents specific to your business or organization
  • Patent documents
  • Specific business agreements
  • Specific intellectual property documents
Custom documents types are less effective if uploaded custom documents are too generic or not specific to your organization, such as:
  • Generic whitepapers
  • Generic datasheets
  • Image or graphic-heavy documents with little text.
For example, your organization both buys and sells software. You want to only detect instances of sensitive customer data contained in invoices for software that you sell. In this case, you can upload a copy of your organization's invoice as a custom document types for fingerprinting.
However, custom document types will be less effective if you wanted to detect receipts for software your organization purchases. This is because there is too much variance in format between the various software vendors your organization purchases from. Greater document variance results in less accurate detection of matched traffic.

Predefined Document Types

Enterprise DLP
provides the following predefined document types.
The predefined document types listed below were originally predefined ML-based data patterns. If you have data profiles using any of the following predefined document types converted from ML-based data patterns:
  • All existing data profile inspection will continue to function as expected.
  • All basic data profiles referencing the converted predefined ML-based data patterns listed below should be recreated to detect the predefined document types.
    A basic data profile is a data profile that includes only data pattern match criteria. Basic data profiles cannot be edited and must be recreated.
  • All advanced data profiles referencing the converted predefined ML-based data patterns should be edited to reference the appropriate predefined document types instead of the predefined ML-based data pattern.
    An advanced data profile is a data profile that includes any combination of data pattern, EDM, and document types match criteria.
  • Bank - Bankruptcy Filings
  • Bank - Statements
  • Financial - Form 1040
  • Financial - Form 1099
  • Financial - Form 1120
  • Financial - Form W-2
  • Financial - Form W-9
  • Financial - Invoice
  • Financial - Paystubs
  • Legal - Business Agreements
  • Legal - Lawsuits
  • Legal - Merger and acquisition
  • Legal - Patent Filings

Recommended For You