Google DeepMind and Singapore GovTech deliver on-device Gemma model for scam detection

What happened

Google DeepMind and Singapore’s Government Technology Agency (GovTech) have delivered a Gemma model fine-tuned on local scam conversations and optimized for typical smartphones in Singapore. A lightweight classifier screens incoming messages before the model evaluates broader conversation context and triggers warnings about suspected manipulation, with conversation processing kept on the device. Training excluded private or personally identifiable information, using anonymized datasets derived from scam reports and intelligence feeds.

Reported by 2 sources

The story so far

Google DeepMind said it and Singapore’s Government Technology Agency (GovTech) have delivered a Gemma-based scam detection model optimized for typical smartphones in Singapore, although its accompanying X post described the work as still being built. The model was fine-tuned on local scam conversations to flag suspected manipulation while processing conversations on the device. A lightweight classifier first screens incoming messages, then the model evaluates the broader conversation context and triggers warnings. Google DeepMind said fine-tuning took place in GovTech’s managed Google Cloud Platform environment, with training data kept isolated. Training excluded private or personally identifiable information and used anonymized datasets derived from scam reports and intelligence feeds. The model was tested against synthetic dialogues and local corpora covering different scam categories and evolving impersonation tactics.

Keep reading

Trending now

1. 1Meta Releases Muse Spark Open With Mac and Cloud Support, Topping US Open-Weight Index
2. 2Google Launches Gemini 4 Argon Globally, Expands Paid Access as Benchmark Results Vary
3. 3OpenAI Updates GPT-6 Astra Pro in ChatGPT With Parallel Agents and Faster Responses
4. 4Meta’s New Business Terms Raise Dispute Over Website Crawling and AI Training Rights