Google is using AI to eliminate 100m spam Gmail messages daily

7 Feb 2019

Image: © vejaa/

Google is using its TensorFlow platform to block millions of spam messages every day.

Google claims that its proprietary machine-learning framework, TensorFlow, is blocking an additional 100m Gmail spam messages on a daily basis.

The platform was launched in 2015 by Google and is an open source framework.

Machine learning help snag unwanted emails

Google has been using AI as well as rule-based email filters for years. While rules can help block glaring examples of spam, machine learning can find new patterns that flag a message as not trustworthy. TensorFlow is also used by companies such as Intel, Qualcomm and Airbnb.

According to Google, TensorFlow is allowing it to block 100m more spam messages from hitting the inboxes of Gmail users every day. The technology giant already claims that existing Gmail filters block 99.9pc of unwanted messages.

Gmail has around 1.5bn users, which means that 100m extra spam messages blocked is not as monumental as it sounds. It actually results in one extra blocked spam email for every 10 Gmail users, The Verge noted.

This does not dismiss the achievement of TensorFlow, though, as the blocking of the additional nuisance emails suggests that Google’s spam-blocking functionality has been enhanced through machine learning.

Spotting unusual spam messages

Google said the machine learning helps to flag certain trickier suspicious messages, such as “image-based messages, emails with hidden embedded content and messages from newly created domains that try to hide a low volume of spammy messages within legitimate traffic”.

Using TensorFlow, Google can identify patterns in massive datasets that humans who create the rules would never be able to catch. When you think about it, emails have thousands of potential signals and just because a certain email meets characteristics that could categorise it as ‘spammy’, does not mean it is actually an unwanted email. Machine learning also lets Google personalise its protections to each user.

Neil Kumaran, product manager of counter-abuse technology at Google, said: “By complementing our existing ML [machine learning] models with TensorFlow, we’re able to refine these models even further, while allowing the team to focus less on the underlying ML framework and more on solving the problem: ridding your inbox of spam.”

Ellen Tannam was a journalist with Silicon Republic, covering all manner of business and tech subjects