Gmail now has better spam filtering capabilities. Google has revealed intentions to deactivate inactive accounts. The company is now rolling out an update that uses artificial intelligence (AI) filters to reduce spam emails.
Scammers can evade traditional spam filters by employing special characters and emoji. The new method, known as RETVec (Resilient and Efficient Text Vectorizer), promises to improve spam protection.
Google claims that the new method is 38% more effective at detecting spam emails and reduces false positives by up to 19.4%. The company appears to have been quietly testing the technology before its release.
With the new system in place, users can worry less about flagging emails as junk in their inbox and dedicate their time to important emails. Google’s new algorithm should be able to detect phishing email campaigns more reliably than before.
Users do not need to do anything to enable the new feature. In fact, Google is currently rolling out the new spam filter globally. When the upgraded system is operational, Google will not notify users. Perhaps the only change you’ll see is the less number of spam emails.
Google’s Cybersecurity & AI Research Director Elie Bursztein and Software Engineer Marina Zhang wrote a blog about RETVec. “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%.”
Also Read:
“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 states. “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.”