After demoing at I/O 2024 in May, Google is rolling out real-time Scam Detection for phone calls on Pixel devices.
Scam Detection listens for “conversation patterns commonly associated with scams.” Once recognized, an audio and haptic alert will prompt you to look at your phone for a “Likely scam” visual warning. “Suspicious activity detected for this call” is accompanied by an “End call” button, or the ability to mark “Not a scam.”
For example, if a caller claims to be from your bank and asks you to urgently transfer funds due to an alleged account breach, Scam Detection will process the call to determine whether the call is likely spam
On the Pixel 9 series, Scam Detection is powered by Gemini Nano. This safety feature is also available on the Pixel 6-8a thanks to “other robust Google on-device machine learning models.”
Google says “no conversation audio or transcription is stored on the device, sent to Google servers or anywhere else, or retrievable after the call.” Scam Detection is off by default and has to be enabled by the user. It can be disabled from Phone app settings, with the option to turn it off “during a particular call.”
Scam Detection is rolling out now to “English-speaking Phone by Google public beta users in the U.S. with a Pixel 6 or newer device.” [Beta Program]
Meanwhile, Google Play Protect’s live threat detection will send a real-time “Unsafe app found” if something is detected. Google is focusing on stalkerware (“code that may collect personal or sensitive data for monitoring purposes without user consent”) at launch before expanding “to other types of harmful apps in the future.”
By looking at actual activity patterns of apps, live threat detection can now find malicious apps that try extra hard to hide their behavior or lie dormant for a time before engaging in suspicious activity.
This is live for the Pixel 6+ and powered by Private Compute Core. Live threat detection is “coming to additional phone makers in the coming months.”
FTC: We use income earning auto affiliate links. More.