Skip to main content

Check out Interactive Visual Stories to gain hands-on experience with the SSE product features. Click here.

Skyhigh Security

Create a Classification using ML Auto Classifier

Advanced DLP: ML Auto Classifiers (an advanced DLP capability) require additional entitlement. Contact Skyhigh Support or your account manager for assistance.

Skyhigh provides ML Auto Classifiers to automatically detect and classify sensitive files based on Skyhigh pre-trained Artificial Intelligence (AI) and Machine Learning (ML) models. You can use Skyhigh predefined ML auto classifiers to identify various types of sensitive files such as financial reports and statements, patient records, patents, source code, and ID files in Sanctioned or Shadow/Web services. For details, see ML Auto Classifiers.

Enable Non-English Language Model for ML Auto Classifier
Limited Availability: The non-English language model for ML Auto classification is a limited availability feature. To enable this feature, contact  Skyhigh Support.

The ML Auto Classifier now supports five non-English languages for the Skyhigh predefined classifier Financial Reports and Financial Statements.  This enhancement extends machine-learning capabilities to accurately identify and classify financial and trade documents in French, German, Spanish, Japanese, and Korean. 

Organizations can effectively manage and protect sensitive financial and trade-related data across global operations with this multilingual capability. It also ensures that financial reports and statements in these languages are properly classified, supporting security compliance.

NOTE: Currently, only one additional language can be enabled per tenant. To enable the required language for your tenant, contact Skyhigh Support.

Define DLP Policies with ML Auto Classifier

The ML Auto Classifier classification method allows you to define ML Auto Classifiers, which can be used to match, process, and protect sensitive files during the DLP policy evaluation. This AI and ML-based data classification method helps to identify, manage sensitive files, and protect sensitive data, leaving your organization.

You can create ML Auto Classifier conditions using predefined categories provided by Skyhigh to accurately identify specific files. These conditions match files against ML Auto Classifiers to trigger remediation actions. These conditions can be configured using condition operators such as:

  • is. Matches files if the selected ML-Auto Classifier is triggered.
  • is one of. Matches files if any one of the selected ML-Auto Classifiers is triggered.
  • is all of. Matches files if all of the selected ML-Auto Classifiers are triggered.
  • is not. Matches files if the selected ML-Auto Classifiers is not triggered.
  • is none of. Matches files if none of the selected ML-Auto Classifiers are triggered.

By using these conditions in the automated classification method, you can define DLP policies to enforce tighter DLP policy controls on sensitive files such as personally identifiable information (PII), financial records, healthcare data, and intellectual property. This ensures the security of your sensitive data across your organization.

For example, you can create a classification using the ML Auto Classifier condition to automatically discover and categorize various types of financial files.

To create a classification using ML Auto Classifier:

  1. Log in to Skyhigh CASB.
  2. Go to Policy > DLP Policies > Classifications.
  3. Click Create Classification
    • Classification Name. Enter a name for this classification. For example, enter Financial Classification. Enter an optional description to describe its use or purpose.
      clipboard_e53405bd182f08d24494f648ad75ab362.png
    • Category. Select a Category from the list. For this example, select Finance and Trade.
    • Conditions. For IF, select ML Auto Classifier. The ML Auto Classifier cloud card appears.
      clipboard_e1172c019e6de32212a9052b718daeaa1.png 
  4. Select an ML Auto Classifier from the list of supported ML Auto Classifiers and click Done. For example, select Finance and Trade (including Financial Reports and Financial Statements).
    • Finance and Trade
      • Financial Reports
      • Financial Reports (French, German, Spanish, Japanese, and Korean)
      • Financial Statements
      • Financial Statements (French, German, Spanish, Japanese, and Korean)
        clipboard_ec9c89c54a0bdba021580004004e4ae9f.png
    • Healthcare
      • Patient Records
    • Intellectual Property
      • Patents
      • Source Code
    • PII
      • ID Documents (Image)

NOTE: The ML Auto Classifier now supports identifying Financial Reports and Statements in five new languages: French, German, Spanish, Japanese, and Korean. Currently, only one additional language can be enabled per tenant. To enable the preferred language for your tenant, contact Skyhigh Support.

  1. Condition Operators. Select an operator for your condition based on your use case. Adding condition operators for your ML Auto classifiers enforces strict DLP policy controls on sensitive files during DLP Policy evaluation. For example, select is one of for ML Auto Classifiers. To understand the functionality of each Condition operator, see Condition Operators for DLP Classification.
  2. Click Save.

Your new Classification is saved to the selected category in the Classifications page. Add the classification to your DLP policies as required.​​​​​​

  • Was this article helpful?