# Google DeepMind — Google DeepMind and Singapore Government collaborate to build fine-tuned AI model for scam detection

- Company: Google DeepMind (deepmind.google)
- Announced: 2026-10-14T02:00:14+00:00
- Category: not stated
- Coverage: 2 outlets
- Announcement: no
- Group: covered
- Source: https://deepmind.google/blog/on-device-ai-scam-detection-mddi/
- Record: https://forck.live/items/21817-google-deepmind-and-singapore-government-collaborate-to-build-fine-tuned-ai
- Subject: Gemini
- Models affected: Gemma

Google DeepMind and the Government Technology Agency of Singapore (GovTech) fine-tuned a lightweight Gemma model for on-device scam detection, using local scam conversations to distinguish benign chatter from manipulation. The model runs on typical smartphones, processing conversation data locally to preserve privacy, and triggers real-time warnings when manipulative patterns are detected.

## Evidence

Verbatim from https://deepmind.google/blog/on-device-ai-scam-detection-mddi/:

> To address this, Google DeepMind's lightweight Gemma model was fine-tuned on local scam conversations. These ranged from impersonations of public institutions, banks, and local figures, to trending regional schemes, ensuring the model can distinguish benign social chatter from genuine manipulation.

## Around this story

Outlets this record can name and link:

- Madrobot — Google DeepMind trained an AI on Singapore’s scams to catch fraudsters inside your chats: https://madrobot.blog/2026/10/14/google-deepmind-govtech-singapore-gemma-on-device-scam-detection

## Follow-ups

- Unite.AI (reported, 14 Oct): Google DeepMind and GovTech Unveil On-Device Scam Detection Model — https://forck.live/items/21848-google-deepmind-and-govtech-unveil-on-device-scam-detection-model

---

Record: https://forck.live/items/21817-google-deepmind-and-singapore-government-collaborate-to-build-fine-tuned-ai
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md