AI/ML, Threat Intelligence, Phishing

Google to deploy AI-powered scam detection in Chrome

Google Chrome application icon on Apple iPhone X screen close-up. Google Chrome app icon. Google Chrome application.

Google is rolling out a new anti-scam feature in Chrome that uses its on-device Gemini Nano large language model to identify and block tech support scams in real time, reports BleepingComputer.

The scams often involve deceptive full-screen warnings or pop-ups falsely claiming system infections to prompt users to call fraudulent helplines. The new detection mechanism is part of Chrome's 'Enhanced Protection' and will debut in Chrome version 137, scheduled for release this week. The system analyzes web content locally using Gemini Nano to detect known scam indicators. If a threat is suspected, Chrome sends the models findings and associated metadata to Google Safe Browsing for further analysis. If verified as malicious, Chrome will issue a user-facing alert. Google emphasizes that the process is designed to maintain privacy and minimize system performance impacts by running analyses asynchronously and limiting GPU usage. Initially available to users who enable Enhanced Protection, the feature will be expanded in future updates to detect other scam types, such as fake delivery notices. Support for Android is expected in 2025.

An In-Depth Guide to AI

Get essential knowledge and practical strategies to use AI to better your security program.

Get daily email updates

SC Media's daily must-read of the most current and pressing daily news

By clicking the Subscribe button below, you agree to SC Media Terms of Use and Privacy Policy.

You can skip this ad in 5 seconds