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

Summary

Google DeepMind and GovTech Singapore fine-tuned a lightweight Gemma model on local scam conversations to detect manipulative conversational patterns on-device. The two-stage pipeline screens inbound messages with a low-power classifier, then analyzes a larger conversation snapshot to confirm threats. The model was developed within GovTech Singapore's managed GCP environment and excluded personally identifiable information.

Related items

• Infollm-gemini 0.35Same vendor · Simon Willison's Weblog
• LowAnthropic warns self-replicating AI could spread to your smart devicesSame vendor · BleepingComputer
• InfoDeveloping Gemini 4 Argon responsibly and safelySame vendor · DeepMind Safety Research
• InfoGemini 4 Argon for RoboticsSame vendor · DeepMind Safety Research
• InfoGemini 4 Argon: Built to solve your hardest problemsSame vendor · DeepMind Safety Research