WhatsApp has begun rolling out a new optional “Scam Alert” feature, which uses a local machine learning model to warn users when scammers are targeting them.
Scam Alert is now available as part of a limited beta rollout while the company tests this new warning system with researchers in its Bug Bounty community.
“Today, we’re sharing an early look at Scam Alert, a new, optional feature that runs an on-device machine learning model to alert a user about potential scam messages,” WhatsApp said. “No message content leaves the device for classification or is auto-reported to WhatsApp, Meta, or anyone else. The feature complements end-to-end encryption while enabling a user-controlled, optional scam alert when the model believes there’s a likely scam.”
The model is trained on scam conversations reported by users and is designed to check whether incoming messages from non-contacts match known scam patterns using linguistic signals and probabilistic classification based on conversational structure.
If it detects a potential scam attempt, the user will see a chat warning asking them to block, report, or continue the conversation.
“If they decide that a warning is incorrectly flagged, the user can mark the chat as trusted, in which case the warning is removed and Scam Alert will not flag that chat again,” WhatsApp added. “If a user marks that they trust a chat, they can also opt in to share the last 5 messages received with WhatsApp to help improve the feature’s accuracy.
According to the company, the message data processed by the local model and the model itself never leave the device, and the user can disable the new Scam Alert feature at any time.
This is part of a broader effort to protect WhatsApp users from scammers, as shown by previous updates that introduced new security features designed to help catch fraud attempts before users engage with them.
In March, Meta announced that WhatsApp will warn users when behavioral signals suggest that a device-linking request may be fraudulent, a common tactic used to hijack accounts by tricking users into scanning a malicious QR code or sharing a linking code.
Two months earlier, it also started rolling out “Strict Account Settings,” a new WhatsApp lockdown-style security feature that protects journalists, public figures, and other high-risk individuals from various sophisticated threats, including spyware attacks.
The feature was introduced after many journalists, activists, and political figures had their phones infected with spyware (including NSO Group’s Pegasus) via messaging apps like WhatsApp in attacks involving zero-click exploits, which allow threat actors to hack iOS and Android devices without user interaction.
WhatsApp’s messaging service is used by over 3 billion people from more than 180 countries to communicate with their family and friends.
Overall prevention scores can hide what happens after initial access. Once attackers are using valid credentials, prevention drops sharply.
The Blue Report 2026 measures defenses technique by technique across 338 million simulations run in customer production environments.
