WhatsApp is reportedly rolling out the Scam Alert feature to beta testers with WhatsApp beta for Android 2.26.34.1.
Scam Alert downloads a machine learning model to the device
Photo Credit: Reuters
Meta officially detailed WhatsApp's upcoming Scam Alert feature earlier this month. The feature, designed to help users detect potential scam messages from unknown contacts, has now entered the testing phase. Select Android beta users are reportedly receiving the feature, indicating that the official rollout is around the corner. The Scam Alert feature is optional feature and it uses an on-device machine learning model to alert a user about potential scam messages.
As spotted by WABetaInfo, WhatsApp is rolling out the Scam Alert feature to a limited number of Android beta testers with version 2.26.34.1. This functionality runs an on-device machine learning model to alert users about potential scam messages. When it identifies a message as a likely scam attempt, it shows a warning in the chat. This allows the user to block, report, or continue the conversation.
The report includes screenshots showing how Scam Alert works and protects users from suspicious accounts. It can be manually enabled by heading to Settings > Account. WhatsApp already confirmed that it is an optional feature and complements end-to-end encryption. Android beta testing of the Scam Alert feature suggests that the general release will likely take place soon.
Meta officially offered an early look at Scam Alert earlier this month. It confirmed that Scam Alert downloads a machine learning model to the device. The model then runs inferences to classify whether incoming messages from non-contacts match known scam patterns.
When the model identifies a message as a likely scam attempt, the user sees a warning in the chat, which is not visible to the other person. If the warning is shown incorrectly, the user can mark the chat as trusted. This will remove the warning, and Scam Alert will not flag that chat again. Users can also share their last five messages with WhatsApp to help improve the feature's accuracy.
The social media giant confirmed that the model is trained on patterns observed in scam conversations from reports that users have sent to them. Meta also stated that the message content is not automatically reported to WhatsApp, Meta, or any third party as part of this process.
Get your daily dose of tech news, reviews, and insights, in under 80 characters on Gadgets 360 Turbo. Connect with fellow tech lovers on our Forum. Follow us on X, Facebook, WhatsApp, Threads and Google News for instant updates. Catch all the action on our YouTube channel.