WhatsApp is testing a new AI-powered “Scam Alert” feature designed to identify potentially fraudulent messages and warn users before they interact with suspicious conversations. The system runs directly on a user’s device and analyses conversation patterns and linguistic cues associated with scams. The model has been trained on patterns identified in conversations showing signs of fraud that were reported to the company through user complaints. It assesses the structure of a conversation and language used to determine the likelihood that a message may be part of an attempted scam.
When the system identifies a message as potentially fraudulent, a warning appears within the chat and is visible only to the user. The person can then decide whether to block the other party, report the issue or continue the conversation.
Scam Detection Runs Directly on User’s Device
Meta says the Scam Alert system performs its classification on the device, meaning message content does not leave the user’s device for the detection process while the feature is enabled.
The company says data is not automatically sent to Meta or other organisations as part of the classification process. This approach is intended to allow suspicious conversations to be assessed while keeping the analysis on the device.
Users who believe a conversation has been incorrectly flagged can add the chat to a trusted list. Once added, the system will no longer check that conversation.
WhatsApp also provides an option for users to voluntarily send the last five messages received through the platform to help improve the accuracy of the model.
Users Can Block, Report or Continue Suspicious Chats
The warning is intended to give users an opportunity to reconsider suspicious interactions before taking further action. After receiving an alert, users retain control over whether they block the sender, report the conversation or continue communicating.
The feature can be enabled or disabled through the settings and is currently available as part of a limited beta test.
The system focuses on conversational patterns associated with fraud rather than simply checking an isolated message. This allows it to consider linguistic cues and the way a suspicious interaction develops.
The feature comes amid substantial losses linked to online fraud. According to figures attributed in the report to the US Federal Trade Commission, WhatsApp users lost $425 million to fraudulent schemes in 2025. The figure was described as part of total social media fraud losses exceeding $2.1 billion.
Fake Money Transfers and ‘Pig Butchering’ Scams Among Key Threats
Among the common fraud methods cited are schemes involving fake money transfers and so-called “pig butchering” scams.
Such scams can involve fraudsters gradually building trust with potential victims before attempting to persuade them to transfer money. This makes the development of a conversation itself an important potential indicator of fraudulent activity.
By analysing conversational structure and linguistic signals on the device, WhatsApp’s Scam Alert feature is designed to identify warning signs before users proceed further with potentially fraudulent interactions.
The limited beta test will provide an opportunity to assess the system’s effectiveness, while users who encounter incorrect warnings can designate conversations as trusted. The feature represents an attempt to use artificial intelligence to identify scam-related behaviour while keeping automated message classification on the user’s device.
About the author — Ayesha Aayat writes on cybercrime, digital safety, and emerging online threats. Her work focuses on public awareness, legal clarity, and technology-driven risks.
