The company announced today that it is bringing early phishing detection to its email service by using machine learning along with click-time warnings for malicious links found in emails as well as unintended external reply warnings.
Currently phishing detection and click-time warnings are available to those using the consumer version of Gmail, but now enterprises will be able to take advantage of these features as well.
Google has already been leveraging the power of machine learning to block spam and phishing messages from showing up in our inboxes with a great deal of accuracy. According to the company, Gmail can prevent these types of malicious messages “with over 99.9 per cent accuracy.” The whole process has its own dedicated machine learning model that delays messages on a selective basis in order to perform meticulous analysis of the emails in question.
Google's detection model utilises its own Safe Browsing service which contains a list of URLs known by ISPs, Chrome and other browsers to contain malware or phishing content. Gmail is then able to use this data to generate new URL click-time warnings for malicious links and the company has stated that the service will continue to improve over time.
In an effort to prevent data loss, Gmail is now able to display unintended external reply warnings to its users. Anytime someone tries to send an email to another user who does not have the same company domain, a quick warning will be shown to make sure that they did in fact intend to send that email. However, existing contacts and recipients from previous emails will not cause Gmail to flash a warning message.
Google's new security features are designed to protect its users even further by preventing “millions of additional emails that can harm users.” The new features are available now and will hopefully keep you and your organisation safer online.
Image Credit: Antb / Shutterstock