Google Messages introduces cloud-based scam defense for Android

Google is expanding its anti-spam tools for Android users by rolling out an Enhanced Protection mode for its Messages app. The feature follows an announcement made earlier this month and adds a higher tier of security above the existing Standard Protection, which already filters spam and harmful links.

The new mode centers on Scam Detection, a system that relies on cloud-based Gemini models to evaluate the context of message threads. Google states that this approach identifies the intent of unknown senders more quickly than previous on-device methods, particularly against novel attacks. To safeguard user data, the system utilizes Android's Private AI Compute, encrypting messages within a secure space that Google says is private to the user and inaccessible even to its own servers.

A second component, enhanced link protection, combines the on-device Gemini Nano model with real-time web signals to verify unfamiliar URLs before a user taps them. This specific capability is currently limited to the Pixel 10 and newer, the Samsung Galaxy S26 series, the Galaxy Z Flip 8 and Z Fold 8, and other select devices.

The update also redesigns warning alerts for links sent by unsaved numbers, providing users with more context and time to pause before opening a connection. Enhanced Protection is opt-in, meaning it does not activate automatically.

Users can enable the feature by navigating to Protection and safety in the Google Messages settings. The menu now lists three distinct options: Enhanced protection, Standard protection, and No protection, with the latter labeled as not recommended. The option has appeared in the latest Google Messages beta, version 20261020_00_RC00.