Google Chrome will add a series of features based on machine learning

Google developers made known through an announcement that in their web browser, Google Chrome, a number of new and updated security features will be integrated, most of which are based on machine learning (ML) models, along with some nifty new ML-based features that aim to make web browsing a bit easier, including a new feature that will suppress notification permission requests when your algorithm believes that it is unlikely to accept them.

Starting with the next version from Chrome,Google introduce a new ML model which will block many of these notification permission requests.

Google Chrome has a built-in phishing detection which scans pages to see if they match known fake or malicious sites. This time, this technology has benefited from improvements. For example, Google says that in Chrome 102, Chrome will rely on machine learning that runs entirely in the browser to help identify websites that ask for unsolicited permissions for notifications and block them, even preventing them from appearing.

“Safe Browsing in Chrome helps protect billions of devices every day, by displaying warnings when people try to navigate to dangerous sites or download dangerous files (see the big red example below). Starting in March this year, we implemented a new ML model that identifies 2,5 times more potentially malicious sites and phishing attacks than the previous model, resulting in a safer web.

“To further enhance the browsing experience, we are also evolving the way people interact with web notifications. For one thing, page notifications help send updates to the sites you care about*; on the other hand, notification permission requests can become a nuisance. To help people navigate the web with minimal disruption, Chrome predicts when permission requests are unlikely to be granted based on how the user has previously interacted with similar permission requests, and silences those unwanted requests. In the next version of Chrome, we will release an ML model that makes these predictions entirely on the device.

In a future version, Google plans to use the same technology to adjust the toolbar of Chrome in real time, making different buttons, like icons to share or voice search, appear when and where you're likely to use them.

As for other functions new ones based on machine learning, Chrome too is getting a new language identification model which better determines what language a given page is in and whether it should be translated accordingly to help people retrace their steps online. For example: You could spend weeks planning a visit to a national park: researching attractions, comparing flights, and shopping for gear. With ML and Journeys, Chrome pulls together the pages you've visited on a given topic and lets you easily pick up where you left off (instead of scrolling through your browser history).

“When you get back to those hiking boots and camping guides, we also use ML to make those websites available in the language of your choice. In particular, we released an updated language identification model to determine the language of the page and whether it needs to be translated to match your preferences. As a result, we see tens of millions of successful translations every day.”

The Chrome team says its goal is "to build a browser that is truly and continuously useful, and we're excited about the possibilities that ML has to offer."

“Every time you come to a new page, Chrome evaluates a collection of signals about the page to see if it matches those from phishing sites. To do this, we compare the colorimetric profile of the visited page, that is, the range and frequency of colors present on the page, with the colorimetric profiles of the current pages. For example, in the image below, we can see that the colors are mostly orange, followed by green, and then a touch of purple.

“This benefits you in two ways when you use Chrome. First, using less CPU time to do the same work improves overall performance. Less CPU time means less battery consumption and less time with fans spinning.

Finally, if you are interested in being able to know more about it, you can consult the details In the following link.


The content of the article adheres to our principles of editorial ethics. To report an error click here!.

A comment, leave yours

Leave a Comment

Your email address will not be published.



  1. Responsible for the data: AB Internet Networks 2008 SL
  2. Purpose of the data: Control SPAM, comment management.
  3. Legitimation: Your consent
  4. Communication of the data: The data will not be communicated to third parties except by legal obligation.
  5. Data storage: Database hosted by Occentus Networks (EU)
  6. Rights: At any time you can limit, recover and delete your information.

  1.   second said

    Yes, and then a page blocks you that you are not interested in being blocked because you use it regularly and nothing has ever happened to you, but they do not offer a white list, for the pages that it blocks you, but you are interested in continuing to access them, add them to said list and so it doesn't get blocked next time, that's why I stopped using chrome as my primary browser and use palemoon and now chrome is my secondary browser.