WhatsApp rolls out new feature that flags potential scam messages
WhatsApp has begun limited beta testing of an optional “Scam Alert” feature that uses an on-device machine learning model to warn users about potential scams. The company is testing it with researchers in its Bug Bounty community.
The model is trained on scam conversations reported by users and checks incoming messages from non-contacts for known scam patterns using linguistic signals and conversational structure. Message content and the model never leave the device for classification, and nothing is automatically reported to WhatsApp, Meta or anyone else.
If a potential scam is detected, users can block, report or continue the conversation. If a warning is incorrect, they can mark the chat as trusted, removing the warning and preventing future alerts for that chat. They can also choose to share the last five messages with WhatsApp to improve accuracy. The feature can be disabled at any time.
The rollout is part of WhatsApp’s broader effort to combat scams. In March, Meta announced warnings for potentially fraudulent device-linking requests, which scammers use to hijack accounts through malicious QR codes or linking codes. Two months earlier, WhatsApp began rolling out “Strict Account Settings,” a lockdown-style feature for journalists, public figures and other high-risk users facing threats including spyware and zero-click attacks.
WhatsApp is used by more than 3 billion people in over 180 countries.
CBN – Maybe they can figure out how to to stop spam text messages 🤬
