Google DeepMind and GovTech Unveil On-Device Scam Detection Model

Google DeepMind and Singapore's GovTech launched an on-device scam detection AI model that warns users about manipulative conversations in real time without sending private messages to the cloud, addressing an urgent problem of over S$4 billion in scam losses since 2019. The model uses a two-stage pipeline to efficiently analyse message context locally and is designed for integration by messaging platforms and OS vendors to enhance user security while preserving privacy.

This Wire brief sits within Fusion42's coverage of Cybersecurity, and 4 sources have reported it between 14 Oct 2026 and 16 Oct 2026.