To detect fraudsters in conversations.. “WhatsApp” launches an artificial intelligence feature

The new tool, called “Scam Alert,” relies on artificial intelligence to analyze messages received from unknown numbers, as it studies “conversation structure and linguistic signals” to assess the possibility that the message is part of a scam.

When the system suspects fraudulent intent, it displays a warning within the conversation that is hidden from the other party, and gives the user the freedom to choose to block the sender, report him, or continue the conversation as usual.

The user needs to activate the feature manually via settings. Once activated, the application downloads a machine learning model that runs locally on the user’s device, which means that “Meta”, the parent company that owns “WhatsApp”, does not receive any copy of the content of the conversations, nor does it share it with any third party, according to the company’s assurances.

However, WhatsApp confirms that it collects certain technical data in a completely anonymous manner, in order to ensure the effectiveness of the feature and its continued updating to keep pace with the latest fraud methods.

The fraud alert system was built on previous conversations reported by users as fraud attempts, and was used to train the AI ​​model to recognize suspicious messages.

The feature is currently being released in a limited trial version to a group of early users, and WhatsApp plans to conduct extensive tests of the system and called on researchers to report any vulnerabilities, before it is circulated to all users at a later stage. (Russia Today)