# Singapore and Google DeepMind Deploy a Fine-Tuned On-Device Gemma Model to Flag Scams Inside Private Chats

A lightweight classifier screens incoming messages and hands suspicious conversations to a Gemma model trained on local scam patterns, with no chat content sent to the cloud.

- Published: 2026-10-15T06:37:42.045Z
- Canonical: https://polylog.news/ai/2026-10-15/singapore-and-google-deepmind-deploy-a-fine-tuned-on-device
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google DeepMind](https://deepmind.google/blog/on-device-ai-scam-detection-mddi/), [Unite.AI](https://www.unite.ai/google-deepmind-and-govtech-unveil-on-device-scam-detection-model/), [Tech Times](https://www.techtimes.com/articles/329042/20261014/singapore-google-deepmind-deploy-device-ai-that-detects-scams-without-cloud-access.htm), [TechBytes](https://techbytes.app/posts/google-deepmind-singapore-on-device-ai-scam-detection-gemma/)

Google DeepMind and the Government Technology Agency of Singapore (GovTech) built a fine-tuned on-device model that detects conversational scams in private chats without sending data to the cloud. Josephine Teo, Singapore's Minister for Dig…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-15/singapore-and-google-deepmind-deploy-a-fine-tuned-on-device (subscription information: https://polylog.news/pricing).