WhatsApp tests on-device AI feature to detect scam messages

WhatsApp is testing a new security feature called ‘Scam Alert’ for select Android beta users. The tool is designed to detect potential fraudulent messages from unknown contacts while maintaining the platform’s end-to-end encryption.

The feature utilizes an on-device machine learning model to analyze the linguistic patterns and conversational structures of incoming messages. Because the processing occurs locally on the user’s device, the content of the messages is not sent to Meta or WhatsApp servers, ensuring privacy is preserved during the detection process.

When a message is flagged as suspicious, a warning is displayed only to the recipient. Users can then choose to block and report the sender, or mark the conversation as trusted to remove the warning. This initiative aims to combat sophisticated social engineering and impersonation scams without compromising user privacy.