Microsoft has started rolling out a new scareware blocker in its Edge browser this week. The AI-powered feature runs on Windows PCs and can identify and block existing scams, and even detect new and emerging ones thanks to a local machine learning model.

“Scareware blocker adds a new, first line of defense to help protect the users exposed to a new scam if it attempts to open a full screen page. Scareware blocker uses a machine learning model that runs on the local computer,” explains the Microsoft Edge team in a blog post. “The model uses computer vision to compare full screen pages to thousands of sample scams that the scam-fighting community shared with us. The model runs locally, without saving or sending images to the cloud.”

Once a scam has been detected, Microsoft Edge will automatically exit the full screen mode that malicious sites try to enforce, stop audio playback, and then warn you with a thumbnail of the page you were viewing. You can then report the site so it’s added to Microsoft’s Defender SmartScreen service that automatically blocks Edge users from visiting known scam sites.

Announced originally at Ignite in November, the scareware blocker in Microsoft Edge is now available in preview in the latest stable channel release of the browser. You’ll need to enable the scareware blocker manually in Edge’s privacy settings, and then restart the browser to get the preview feature.