Phishing Classifier Demo Output Parameters - Administrator Guide - 6.10 - Cortex XSOAR - Cortex - Security Operations

TextTokensHighlighted

The text of the email message with the highlighted positive words (if found).

Label

The predicted label of the message.

Confidence

The confidence of the label (between 0-1). The higher this value, the more confident the classifier is in its prediction.

PositiveWords

The words that encouraged the model to make the prediction.

NegativeWords

The words that are in general not correlated with the prediction class and reduced the model’s confidence in its prediction. For example, !DBotPredictOutOfTheBoxV2 emailBody="this is a test email. do not delete. Click http://phishing-emails.com", returned a Non-malicious label, confidence 0.54 and the negative words were a, email.