● Covered by 4 sources · 4 reportsMedium impact4 neutral
WhatsApp Rolls Out Optional On-Device Scam Alert Feature in Limited Beta
Key points
- Scam Alert is an optional feature in limited beta.
- Uses on-device machine learning to detect scams.
- Maintains end-to-end encryption by local processing.
- Users receive warnings for suspicious messages from non-contacts.
- Users can report, block, or mark chats as trusted.
Introduction of Scam Alert
WhatsApp has initiated a limited beta rollout of its new "Scam Alert" feature. This optional tool is designed to help users identify potential scam messages received from unknown contacts. The feature operates by employing an on-device machine learning model to analyze incoming messages.
The primary goal of Scam Alert is to enhance user safety against evolving scam tactics, including impersonation and social engineering, while upholding the platform's commitment to end-to-end encryption.
On-Device Processing and Privacy
A key aspect of Scam Alert is its privacy-preserving design. The machine learning model is downloaded to the user's device, and all message classification occurs locally. This ensures that no message content leaves the device for analysis or is automatically reported to WhatsApp, Meta, or any third party.
This on-device processing allows the feature to work in conjunction with end-to-end encryption, meaning message content remains encrypted and private even while being scanned for scam patterns.
How the Feature Works
Once enabled, the on-device model evaluates incoming messages from non-contacts for patterns associated with known scams. It analyzes conversational structure and linguistic cues. If a message is flagged as a potential scam, only the recipient sees a warning within the chat; the sender is not notified.
Users have several options when a message is flagged: they can block the contact, report the message, ignore the warning, or mark the conversation as trusted. Marking a chat as trusted will suppress future alerts for that specific conversation. Users can also choose to share the last five messages received from a trusted chat to help refine the model's accuracy.
Transparency and Model Integrity
To ensure the integrity and transparency of the machine learning models, WhatsApp states that every model release must be logged on a third-party, append-only transparency ledger before distribution. This measure aims to prevent the pushing of specific models to specific individuals.
The company is also engaging with its Bug Bounty community and the broader security research community to stress-test the system and gather feedback on its implementation.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
How outlets covered it
Meta is rolling out an optional Scam Alert feature for WhatsApp that uses on-device machine learning to identify and flag suspicious messages. This feature aims to combat the significant scam activity on the platform, which has resulted in substantial financial losses for users.
WhatsApp has begun a limited beta rollout of "Scam Alert," an optional feature that uses a local machine learning model to identify and warn users about potential scam messages. This feature aims to protect users from fraud by flagging suspicious conversations without sending message content off-device, enhancing user security within the platform.
WhatsApp is rolling out a new, optional "Scam Alert" feature that uses an on-device machine learning model to identify potential scam messages without compromising end-to-end encryption. This feature processes message content locally on the user's device, ensuring no data leaves the device for classification or reporting unless the user explicitly chooses to report it.
WhatsApp has launched a limited beta of Scam Alert, an optional feature that uses on-device machine learning to identify suspicious messages from unknown contacts. This feature aims to protect users from scams while maintaining end-to-end encryption by processing all data locally on the device.