Microsoft Edge to start blocking scareware with new AI feature

Microsoft has introduced an AI-powered Scareware Blocker for its Edge browser, designed to protect Windows PC users from emerging tech support scams.

What’s new: Microsoft Edge’s latest security feature uses machine learning to identify and block scareware attacks, representing a significant advancement in browser-based security protection.

• The feature is currently in preview mode and can be activated through Edge’s Privacy settings
• When activated, the blocker automatically exits full-screen mode and displays warning messages about suspicious sites
• Users can report suspicious sites and share screenshots to help protect others
• The machine learning model operates locally on users’ devices without sending data to the cloud

Understanding scareware: These tech support scams manipulate browser interfaces to create fake virus infection alerts and trick users into calling fraudulent support numbers.

• Scammers modify browser displays to convince users their systems are compromised
• The scam typically includes a fake tech support number that, when called, enables attackers to gain unauthorized access to victims’ computers
• These attacks represent a growing threat to users who may not be able to distinguish legitimate warnings from fraudulent ones

Technical implementation: The Scareware Blocker works in conjunction with Edge’s existing security features to provide enhanced protection against emerging threats.

• The feature complements Edge’s Defender SmartScreen, which already blocks known malicious websites
• Users can access the feature by navigating to Edge Settings > Privacy, search, and services
• The browser must be updated to the latest version to access the Scareware Blocker
• Users can submit feedback when legitimate sites are incorrectly flagged as suspicious

Privacy considerations: Microsoft has designed the feature with user privacy in mind, implementing security measures that don’t compromise personal data.

• The machine learning model operates entirely on the user’s device
• No images or site data are transmitted to Microsoft’s cloud servers
• Users maintain control over the feature’s activation and reporting functions

Looking forward: While this implementation represents a promising step in browser security, its effectiveness will largely depend on user adoption and the ability of the AI model to adapt to increasingly sophisticated scareware tactics. The local processing approach could also serve as a model for future security features that prioritize both protection and privacy.