Google is adding an on-device artificial intelligence (AI) model to Chrome to fight scams. Gemini Nano, a large language model (LLM), will evaluate websites that users visit and alert if potential fraud is detected.
The new feature will be included in Chrome 137, which launches this week, currently in beta.
Google describes it as an additional layer of protection. Gemini Nano will generate signals that “will be used by Safe Browsing to deliver higher confidence verdicts about potentially dangerous sites like tech support scams.”
Initial experiments show that LLMs are relatively effective at understanding and classifying websites.
Running the model on-device helps preserve user privacy, but more importantly, it allows the model to see the threats when users see them.
“We’ve found that the average malicious site exists for less than 10 minutes, so on-device protection allows us to detect and block attacks that haven’t been crawled before,” the Google Chrome security team explains.
Servers can support different versions of websites for different uses, often for legitimate purposes, such as to account for device differences, personalization, or time-sensitive content. However, cybercriminals use this to evade security crawlers.
Gemini Nano will check websites that contain the specific characteristics of tech support scams and extract security signals on the go. This information will be sent to Google’s Safe Browsing server for the final verdict. Chrome will display full-screen warnings for websites that Google determines are likely to be scams.
“Gemini Nano’s LLM is perfect for this use because of its ability to distill the varied, complex nature of websites, helping us adapt to new scam tactics more quickly,” Google explains.
Google assures that the technology will be used sparingly to preserve performance and privacy. The feature will be available only to users who have opted in to the Enhanced Protection mode of Safe Browsing in Chrome.
The detected malicious websites will be added to blocklists to better safeguard Standard Protection users.
“To protect even more users from scams, we are working on rolling out this feature to Chrome on Android later this year,” Google said.
On Android, Google is launching another Chrome AI feature to fight unwanted and fraudulent notifications.
“This new feature uses on-device machine learning to detect and warn you about potentially deceptive or spammy notifications, giving you an extra level of control over the information displayed on your device.”
Chrome will alert users about flagged notifications and let them unsubscribe from abusive websites with a single click.
Google explains that the large language model is trained on the textual contents of the notification, like the title, body, and action button texts.
The new features follow other recently introduced security enhancements. Google recently launched on-device scam detection for Google Messages and Phone apps to block malicious calls and text messages.
To set the Safe Browsing protection level to Enhanced protection, follow these steps on your computer:
- Go to Settings (click three dots at the top right, select Settings).
- On the left, select Privacy and security, and then Security. Here, select the level of “Safe Browsing” you want to use.
Similarly, on Android or iPhone, go to Chrome’s settings by tapping the three dots and selecting Settings, navigate to Privacy and Security, select Safe Browsing, and choose the desired protection level.
Your email address will not be published. Required fields are markedmarked