Meta Engineering Blog

EngineeringAug 12, 2026

How We’re Building Scam Alert on WhatsApp With End-to-End Encryption and Verifiability Guarantees

Meta's WhatsApp implements Scam Alert, a user-controlled, optional feature using on-device machine learning to flag potential scam messages. The feature processes all data on-device, with no automatic reporting to WhatsApp or Meta, ensuring end-to-end encryption and user privacy. Scam Alert is trained on scam conversation patterns from user reports and uses differential privacy to anonymize and minimize data shared with WhatsApp. The feature's design adheres to core principles, including on-device only processing, no automatic reporting, and user control. Message content remains private, and telemetry is processed through a confidential computing environment to provide aggregate and anonymous counts to WhatsApp. The machine learning model is publicly published and verifiable, and users can trust or block chats to refine the feature's accuracy.

SocialScale

1 min

Latest Articles

GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster

How Meta Built Forum With AI-Native Engineering

2026 World Cup: Breaking Records, Spiky Charts and Reliability at Scale

Sapienz Receives ISSTA 2026 Impact Paper Award

Meta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI

OCP Summit 2026: Powering AI with Open Innovations in Scale-Up, Scale-Out, and Scale-Across Networks

Shipping Media Over QUIC at Meta Scale for Instagram Live Ingest

Turning Opportunistic AI Inference Capacity Into Better Ads Recommendations

NTS: Authenticated Time at Meta

Bringing Private Processing to Meta AI Glasses

Open-Sourcing Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems

Inside Petal: Building the World’s First Petabit-Class Transoceanic Subsea Cable

ZGateway: Learnings from Putting a Proxy in Front of ZippyDB

An Organizational Second Brain: Building an AI That Learns From Experts

MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet

MTIA 300: Meta&#8217;s First Training Chip with Built-in NICs and Communication-Offloading Engines

How We’re Building Scam Alert on WhatsApp With End-to-End Encryption and Verifiability Guarantees

From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking

Meta Engineering Blog

Latest Articles

GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Inside Prometheus: Meta’s Journey to a Gigawatt-Scale Supercluster

How Meta Built Forum With AI-Native Engineering

2026 World Cup: Breaking Records, Spiky Charts and Reliability at Scale

Sapienz Receives ISSTA 2026 Impact Paper Award

Meta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI

OCP Summit 2026: Powering AI with Open Innovations in Scale-Up, Scale-Out, and Scale-Across Networks

Shipping Media Over QUIC at Meta Scale for Instagram Live Ingest

Turning Opportunistic AI Inference Capacity Into Better Ads Recommendations

NTS: Authenticated Time at Meta

Bringing Private Processing to Meta AI Glasses

Open-Sourcing Rebalancer: A Generic, High-Performance Library for Solving Assignment Problems

Inside Petal: Building the World’s First Petabit-Class Transoceanic Subsea Cable

ZGateway: Learnings from Putting a Proxy in Front of ZippyDB

An Organizational Second Brain: Building an AI That Learns From Experts

MetaRoCE: A New RDMA Transport Built for AI-Scale Ethernet

MTIA 300: Meta&#8217;s First Training Chip with Built-in NICs and Communication-Offloading Engines

How We’re Building Scam Alert on WhatsApp With End-to-End Encryption and Verifiability Guarantees

From User Sequences to Scaling Laws: A Multi-Stage Architecture for Meta’s Ads Ranking

MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines

MTIA 300: Meta’s First Training Chip with Built-in NICs and Communication-Offloading Engines