Service Update
| Availability | July 8th, 2022 |
| Product(s) | Email Security Cloud Gateway (CG) |
| Who's affected | TTP URL Protection users |
Overview
Mimecast is pleased to announce the release of a new machine learning model that enhances resilience against zero-day and emerging phishing attacks. This is a feature-rich machine learning model for URL classification, designed to target zero-day and emerging threats with a low false-positive rate.
What's changing
The model can analyze URLs when clicked as well as via the Check URL function in the Administration Console. Detections made by the model will be shown in the Targeted Threat Protection (TTP) URL Logs – Scan details section in the Mimecast Administration Console
The model is trained on a high-confidence data set comprised of 1 million samples. With features engineered from a wide variety of elements, such as lexical URL analysis, page content, domain analysis, certificate details, and email content, the model has context beyond the URL alone.
Recommended actions
The machine learning model is fully enabled for customers with TTP URL Protect set to an Aggressive categorization mode.
Action Required: The URL Category Scanning drop-down must be set to aggressive in the URL Protection definition in order to take advantage of this feature.
The Rewrite Mode does not have to be set to Aggressive.
For more information on Rewrite Modes, see Configuring URL Protection Definitions Inbound Settings section.
Comments
Please sign in to leave a comment.