
Google today published a report about how it’s using the latest AI approaches to combat spam across Search, Chrome (with Gemini Nano for Enhanced Protection), and Android.
Google Search credits AI-powered scam detection systems as currently helping detect and block “hundreds of millions of scammy results every day.” The company notes how it can now “analyze vast quantities of text and identify subtle linguistic patterns and thematic connections that might indicate coordinated scam campaigns or emerging fraudulent narratives.”
For example, we’ve observed a significant increase in bad actors on the web impersonating airline customer service providers and scamming people in need of help. We’ve already reduced these scams by more than 80% in Search, greatly reducing the risk that you call a scammy phone number.
In addition to the “Standard Protection” warnings when you come across a nefarious site, Safe Browsing offers an optional “Enhanced Protection” mode against phishing and other scams. Desktop Chrome is now using the on-device Gemini Nano model to “provide Enhanced Protection users with an additional layer of defense against online scams.” The LLM “provides instant insight on risky websites and allows us to offer protection, even against scams that haven’t been seen before.”

Gemini Nano’s LLM is perfect for this use because of its ability to distill the varied, complex nature of websites, helping us adapt to new scam tactics more quickly.
Google is already using this to “protect users from remote tech support scams,” with plans to cover more types and bringing to the Android browser in the future.
Meanwhile, Chrome for Android will use an on-device machine learning model that flags “malicious, spammy or misleading notifications” and labels them as “Possible scam.” Users can “Show notification” or “Unsubscribe.”
Google also reiterates how AI is behind Scam Detection in Google Messages and the Phone by Google app.

FTC: We use income earning auto affiliate links. More.

Comments