WhatsApp Begins Limited Beta Testing of On-Device Scam Alert to Detect Fraud While Preserving End-to-End Encryption

WhatsApp has started limited beta testing of its Scam Alert feature, which uses an on-device machine learning model to analyze message patterns and linguistic indicators of fraud. The system runs entirely locally on the user's smartphone, ensuring that conversation content is never sent to WhatsApp or Meta. Users receive warnings about suspicious messages from unknown contacts and can choose to block, report, ignore, or mark the chat as trusted. To maintain transparency, each model release is logged in an immutable journal managed by Cloudflare with Ed25519 signatures and SHA-256 hashes. The company receives only anonymized statistics on detections and user actions. In parallel, Signal has introduced automatic key verification using a cryptographically verifiable log audited by Cloudflare and Trail of Bits.

AntiMalwareTranslated from Russian

Read at source

WhatsApp, owned by Meta, has launched limited beta testing of its Scam Alert feature designed to warn users about potentially fraudulent messages from strangers.

The protection relies on a machine learning model that runs directly on the smartphone. Conversation content is never transmitted to WhatsApp or Meta, preserving end-to-end encryption. After activation, the device downloads the model and examines dialogue structure along with linguistic signs of fraud.

When a message appears suspicious, the recipient sees a warning while the sender remains unaware. Users can then block the contact, file a report, dismiss the alert, or designate the chat as trusted. In the trusted case, the last five messages can optionally be shared to help improve the model.

To prevent Meta from deploying a customized analyzer to specific users, every model release is recorded in an immutable log. A manifest containing SHA-256 hashes is signed with Ed25519 keys controlled by Cloudflare. The smartphone verifies the signature, log entry, and file integrity before executing the model.

WhatsApp collects only anonymized counters of detections and subsequent user actions. The app also includes a Scam Alert Activity log showing check results and model versions.

The current release remains an early technical preview. Meanwhile, Signal has introduced automatic key verification that uses a cryptographically verifiable log and allows users to confirm no unauthorized intermediary is present. Independent audits are performed by Cloudflare and Trail of Bits without access to user data.

Meridian digestThe week's most consequential security stories, distilled into one briefing.See the digest

More in Fraud & Social Engineering

Scammers Use *#62# USSD Command to Fabricate Surveillance Claims and Steal Victims' Funds
Aroshka Cloud Faces Scrutiny Over Alleged False Claims of SOC 24/7 Operations and High-End Infrastructure
Reports Surface on Alleged De-Anonymization of Admins Running Major Russian Hacker Forums