Microsoft is testing a new “scareware blocker” feature for the Edge browser on Windows PCs, which employs machine learning to detect tech support scams. This feature, introduced at the 2024 Ignite conference in November, is currently available in preview mode for users in the stable channel.
Microsoft introduces scareware blocker for Edge browser
Scareware scams, or tech support scams, have been a longstanding threat, where scammers use aggressive tactics to convince victims that their devices are infected with malware, urging them to call fake support numbers for assistance. Microsoft’s existing Defender SmartScreen also combats these scams by adding known abusive sites to its index of malicious web pages, offering worldwide protection within minutes.
Unlike Defender SmartScreen, the new AI-powered Edge scareware blocker operates in real-time by using 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,” Microsoft stated.
The scareware blocker utilizes computer vision to compare a full-screen page to thousands of sample scams provided by the scam-fighting community. It operates locally, ensuring no images are saved or sent to the cloud. Once a potential scam page is identified, the blocker alerts the user, exiting full-screen mode, halting any sound from the page, and displaying a warning along with a thumbnail of the site.
The 8 main problems with a cluttered browser
To use the scareware blocker, users must ensure that they have the latest version of Edge installed. They can enable it through the “Privacy, Search, and Services” settings after their administrator allows previews. Microsoft advises users to restart the browser after these updates to access the feature.
When the scareware blocker identifies a potentially harmful page, it allows users to report the site by sharing screenshots and diagnostic information with Microsoft, which helps enhance Defender SmartScreen’s capabilities. Users are also encouraged to report false positives to improve the model’s reliability. “By reporting false alarms, you help us make the feature more reliable to catch real scams,” Microsoft remarked.
In addition to the scareware blocker, Microsoft is expected to roll out a brand impersonation protection feature for Teams Chat by mid-February 2025, as announced recently.
Featured image credit: Microsoft
