Google integrates a machine learning model into the Chrome browser to detect potential phishing attacks.

With upcoming on-device machine learning developments #Chromiumblock unwanted notifications, translate more sites into your preferred language, and more.

Learn how we create a safer, more accessible and more personalized experience for you → https://t.co/3dbNPo4P15 pic.twitter.com/fFKWD3n6rv

— Chrome (@googlechrome) 9 June 2022

According to the developers, the algorithm detects 2.5 times more potentially malicious sites and phishing attacks than the previous model. This provides safer and more secure web surfing, according to the company.

Google also announced the integration of an AI model that disables site requests from sending notifications. According to the company, the algorithm analyzes the user’s previous actions and predicts the likelihood of such permissions being granted.

Another model is for optimizing the toolbar in Chrome. Based on the user’s actions, the browser will highlight the interface elements that are most likely to be useful at the moment.

What’s new will appear in the next update of Chrome. The company emphasized that machine learning models will process requests directly on the user’s device.

Recall that in April, Google Lens text recognition was added to Chrome.

In February, browser developers fixed 27 vulnerabilities, including eight high-risk ones.