Your Gmail inbox just got its ‘largest defence upgrade in years’ with new AI that promises to eliminate spam
GETTY IMAGES
New AI-powered filter is 38% better at identifying junk emails, Google says
Use Gmail? Google has just introduced the "largest defense upgrades in recent years" to your inbox.
Provided that Google hasn't deleted your Gmail account this month, the exciting new update, which is slowly rolling out to users across the globe, could eliminate spam emails with its supercharged AI-powered filters.
Cybercriminals have discovered more sophisticated methods to bypass the spam filters built into Gmail. Using special characters, emoji, and homoglyths have enabled scammers to swerve the existing spam filter built into Gmail. But the new system, known as RETVec (Resilient & Efficient Text Vectorizer), aims to put an end to that.
According to Google, the new system is 38% better at identifying spam emails and reduces false positives by as much as 19.4%. To thoroughly test the system ahead of its release, Google was secretly using it inside the company for months — a process known as "dogfooding" in Silicon Valley.
With the defence upgrade in place, you should spend less time flagging emails as junk and more time reading important correspondence in your inbox.
Google's RETec system should keep you safer in every part of your life online, since phishing and smishing email campaigns should also be blocked by the upgraded spam filter — reducing the chance that you mistakenly hand over sensitive information, like your password or payment details, to hackers.
Best of all? If you use Gmail, you don't need to do anything to enable the new feature. Google is slowly pushing out the improved spam filter worldwide at the moment, with the new features updated automatically.
Google won't notify you when the upgraded RETVec system is up and running. With any luck, you'll just notice fewer spam emails landing in your inbox.
Discussing the improvements with its new system, Google Cybersecurity & AI Research Director Elie Bursztein and Software Engineer Marina Zhang penned a blog post about RETVec.
In the post, they write: "Over the past year, we battle-tested RETVec extensively inside Google to evaluate its usefulness and found it to be highly effective for security and anti-abuse applications. In particular, replacing the Gmail spam classifier’s previous text vectorizer with RETVec allowed us to improve the spam detection rate over the baseline by 38%"
"Due to its novel architecture, RETVec works out-of-the-box on every language and all UTF-8 characters without the need for text preprocessing, making it the ideal candidate for on-device, web, and large-scale text classification deployments," the blog post adds. "Models trained with RETVec exhibit faster inference speed due to its compact representation. Having smaller models reduces computational costs and decreases latency, which is critical for large-scale applications and on-device models."
LATEST DEVELOPMENTS
Reducing the computational cost of such an everyday task as spam filtering should reduce the amount of data servers dedicated to Gmail, which boasts a staggering 1.8 billion users worldwide. That's over 20% of the global population ...and a lot of spam emails to check.