Gmail embraces artificial intelligence to combat spam

Gmail offers AI-based spam detection to protect users from unwanted spam messages. The company wants to outsmart scammers with a new text classification system called RETVec.

Our mailboxes are often bombarded with spam messages. World-famous email platform Gmail wants to put an end to this and is turning to artificial intelligence to do so. The new AI-based text classification system RETVec (Efficient and Flexible Text Vector), developed by Google, is a big step forward in the fight against text manipulation.

Detect homophones

After all, a common tactic among scammers is text manipulation. For example, by using homonyms, or visually similar characters, fraudsters can imitate domain names. Classical detection technology cannot track such homogeneous letters. RETVec’s new system, based on machine learning, focuses on visual similarity rather than just letter recognition, allowing it to recognize homogeneous letters. This new technology allows Gmail to better understand and process text processing with advanced spam filters.

A long-term battle

Gmail has been actively improving its spam filters for several years. For example, in 2019, the company identified an additional 100 million spam emails per day using TensorFlow. With RETVec, Google hopes to set a new standard in email security. Currently, the introduction of RETVec has improved spam detection by 38 percent Fake positives It decreased by approximately 20 percent.