Microsoft Edge Introduces AI-Powered ‘Scareware Blocker’ to Combat Online Scams Using Computer Vision
Microsoft is launching a new “scareware blocker” feature for its Edge browser, leveraging machine learning and computer vision to tackle one of the internet’s most persistent scams. Scareware, a deceptive tactic often disguised as fake antivirus software, has plagued users for years by falsely claiming to detect threats on their devices. These scams typically trick users into downloading malware or paying for unnecessary software.
The issue remains widespread. In 2023, two tech support companies were ordered to pay $26 million in a settlement with the U.S. Federal Trade Commission (FTC) for using fake Windows pop-ups and other deceptive practices to defraud consumers, particularly older adults. “These companies used scare tactics and lie about threats to consumers’ personal computers to bilk them out of tens of millions of dollars,” said Samuel Levine, director of the FTC’s Bureau of Consumer Protection.
While Microsoft already blocks known scam websites through tools like Defender SmartScreen, the new scareware blocker focuses on identifying and stopping previously unknown scams in real-time. The feature first previewed at Microsoft’s Ignite conference in November, is now available for testing through Edge’s preview program.
How It Works
Users can enable the scareware blocker in Edge’s “Privacy, search, and services” settings. Once activated, the tool monitors for suspicious full-screen pages—a common tactic scammers use to make their schemes harder to detect or escape. Unlike traditional methods, the blocker uses a machine learning model trained on thousands of real-world scam examples. It employs computer vision to compare new pages against these samples, ensuring it can identify emerging threats.
When the tool detects potential scareware, it automatically exits full-screen mode, halts any accompanying audio (like fake alarms or voices), and prompts the user to either proceed or close the page entirely.
Privacy and Local Processing
Microsoft emphasizes that the scareware blocker operates locally on the user’s device, with no data sent to the cloud. This approach addresses potential privacy concerns, particularly in light of the controversy surrounding Microsoft’s AI-powered Recall feature, which captures and stores screen snapshots.
To further refine the tool, Microsoft is encouraging early adopters to provide feedback. Users can share screenshots of blocked scams or report instances where the tool mistakenly flags legitimate websites.
A Step Forward in Online Security
The scareware blocker represents a significant advancement in combating online fraud, offering an additional layer of protection against evolving scams. By combining machine learning, computer vision, and user feedback, Microsoft aims to create a safer browsing experience for Edge users while maintaining their privacy.
