TechPrufer
Get started
DeepMind
DeepMind logoDeepMind · Feature trail

On-Device Scam Detection

1 post · Oct 2026

What this trail covers

On-device AI models are being developed and deployed for real-time scam detection, prioritizing user privacy and local context. These models are fine-tuned on regional scam data and utilize efficient, multi-stage pipelines to run on user devices, triggering warnings without server-side data access. This approach aims to counter evolving social engineering tactics and protect users from financial and credential exposure.

All DeepMind trails
  1. On-Device AI Against Scams: Google DeepMind & MDDIThis post details the fine-tuning of a lightweight Gemma model for on-device scam detection, specifically tailored to local Singaporean scam tactics. It introduces a two-stage pipeline for efficient processing on smartphones: a lightweight classifier for initial screening and a more in-depth analysis with the fine-tuned Gemma model for confirmation. The development process adhered to strict governance, including training within a Sovereign Sandbox, exclusion of citizen data, and stress-testing against synthetic dialogues and local corpora.