Published: Fri, February 08, 2019
Electronics | By Shannon Stone

[H]ardOCP: Google Uses TensorFlow to Fight Spam Emails

However, Google wants to put that to an end with its new AI, which will block 100 million extra Gmail spam messages per day.

Google LLC is beefing up Gmail's anti-spam capabilities with new protections, powered by its machine learning software framework TensorFlow, that are created to complement its existing algorithms.

This is over and above the 99.9% spam, phishing and malware the company claimed to have blocked out as early as 2015.

Additionally, Google also detailed the new kinds of spam messages that are now being thwarted on Gmail.

Google's Gmail is used by 1.5bn people each month with 5m businesses using the service as part of G Suite and one of the biggest draws of the service is its built-in security protections.

"At the scale we're operating at, an additional 100 million is not easy to come by", Neil Kumaran, product manager of Counter Abuse Technology at Google, told The Verge. Getting the hand on last bit of spam is increasingly hard, but TensorFlow has been great for terminating that gap.

The American tech giant has declared new protectors have arrived for Gmail powered by its own open-source machine learning framework, TensorFlow.

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. Nowadays, spam messages are becoming more and more frequent, starting from annoying newsletters and fake job invitations to a Saudi prince being stuck at an airport. This process has been taking place for years, says Kumaran, with Gmail looking for certain signals from users about what they judge to be spam, but TensorFlow is "turning those signals into better results". Implementation of TensorFlow has helped Gmail block image-based messages, emails with hidden embedded content, and messages from newly created domains that try to hide a low volume of spam messages within legitimate traffic. Hence, integrating TensorFlow with the existing Gmail framework has allowed the latter to personalize the spam filters more effectively.

Google continued: "Where did we find these 100 million extra spam messages?"

Like this: