browse
ML document classification enhances content matching efficacy while also simplifying data loss prevention policy management by allowing customers to select from predefined, pre-trained document types, rather than building complex data classifications from scratch based on terms and patterns.
How to use ML-based Document Classification?
ML-based Document Classification is available as a type of selectable built-in identifier when creating a data classification. All supported ML-based identifiers are available under a new section titled ML Built-in Identifiers as seen in the image below.
What types of documents are currently supported?
Consulting agreements, CVs and Resumes, IRS forms, medical power of attorney, NDA, partnership agreement, stock and US patents.
Which languages and regions are currently supported?
Our initial release is focused on US English language documents. This will expand to include more languages and additional regions in the future.
Is ML Document Classification fully supported by Multimode DLP?
Yes. This feature is supported by both Realtime DLP and SaaS API DLP, and it is compatible with all DLP supported file types.
Where can I find more information?
Refer to the Secure Access and Umbrella documentation for guidance on using the built-in ML-based Data Identifiers to create Data Classifications that can be incorporated into DLP policy rules
Secure Access: Built In Data Identifiers
Umbrella: Built In Data Identifiers