Google is adding a new AI-powered scam protection feature that monitors phone call conversations on Google Pixel devices to detect patterns that warn when the caller may be a scammer.

Google has also added a new real-time protection feature to Google Play Protect that detects when unsafe apps are found on Google Play.

The features have been made available to Google Pixel 6 devices and newer models of the series, but more Android devices from other OEMs are expected to receive them in the coming months.

These real-time protection features are designed to make using Android safer by evading and blocking known dangers.

AI-powered scam scall detection

The first feature Google announced is a new AI-powered anti-scam system that analyzes active phone conversations to detect whether the caller is a scammer.

The system will work in real time by detecting conversation patterns commonly associated with scams, like callers impersonating companies or urgent phone calls following breach alerts.

When a call is detected as a scam, a notification will appear on the phone, warning the Android user and asking if they would like to end the phone call.

Although all processing happens on the device, Google has opted to keep the feature off by default, allowing users to activate it through the Phone app settings or even during a particular call.

The initial rollout of the anti-scam system will only work for conversations made in English, and it is currently rolling out to Google Pixel 6 and later users in the US.

“Gemini Nano, our advanced on-device AI model, powers Scam Detection on Pixel 9 series devices,” explains Google.

“As part of our commitment to bring powerful AI features to even more devices, this AI-powered protection is available to Pixel 6+ users thanks to other robust Google on-device machine learning models.”

Anti-stalkerware system

The second feature is the new “Live Threat Detection” in Google Play Protect, Android’s default anti-malware and security tool that protects users in real-time.

“Play Protect analyzes behavioral signals related to the use of sensitive permissions and interactions with other apps and services,” Google announced.

“With live threat detection, if a harmful app is found, you’ll now receive a real-time alert, allowing you to take immediate action to protect your device.”

The scanning and detection process is handled locally on the device through Android’s Private Computer Core to protect users’ privacy.

Google clarified that, in its initial release, the new system will focus on stalkerware that silently collects data about the victim without their consent and knowledge.

In the future, more types of dangerous apps, potential malware, adware, banking trojans, and spyware will be added.