Gmail is now blocking 100 million more spam messages with TensorFlow

By using TensorFlow's AI technology, it make managing data at this scale easier, while the open-source nature of framework means new research from the community can be quickly integrated.

Initially developed for internal Google use, the TensorFlow open-source machine learning (ML) framework was released under the Apache 2.0 license more than three years ago.

Google says it's blocking 100 million more spam messages a day in Gmail after advancing its machine learning models.

TensorFlow has been added alongside existing Artificial Intelligence (AI) and rule-based filters that Gmail has utilised for years. The rule-based filters are capable of blocking obvious spam, while machine learning look for new patterns which reveal that whether an email is trusted of spam. 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. Moreover, Google, Intel, SAP, Airbnb, and Qualcomm are the top users of this software. It actually results in one extra blocked spam email for every 10 Gmail users, The Verge noted. In the context of Gmail's more than 1 billion users, this isn't necessarily a huge gain.

Launched by Google in 2015, TensorFlow has now become an integral part of its AI algorithms.

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

TensorFlow also helps Google personalise spam protection for each user.

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. It supplements current detection by finding emails with hidden embedded content, image-based messages, and messages from newly created domains that may try to hide a low volume of spam emails within legitimate traffic. TensorFlow Extended (TFX) is one of these components that allows Google to deploy ML pipelines in a quick and standardized fashion while TensorBoard allows it to monitor model training pipelines and quickly evaluate new models to determine their usefulness.

Lonzo Ball Better Than LeBron James? LaVar Ball Says, Yes, Absolutely
Pope reveals the scandal of nuns used as sex slaves