{"version":1,"type":"story","url":"https://digestai.news/story/google-deepmind-and-singapore-launch-on-device-scam-detection-tool","json":"https://digestai.news/story/google-deepmind-and-singapore-launch-on-device-scam-detection-tool.json","markdown":"https://digestai.news/story/google-deepmind-and-singapore-launch-on-device-scam-detection-tool.md","slug":"google-deepmind-and-singapore-launch-on-device-scam-detection-tool","headline":"Google DeepMind and Singapore launch on-device scam detection tool","summary":"Google DeepMind and the Government Technology Agency of Singapore (GovTech) have announced a new on-device AI tool designed to protect citizens from financial scams. This collaboration, part of the National AI Partnership, addresses a critical issue where scams account for over half of reported crimes in Singapore and have caused more than S$4 billion in losses since 2019. The tool specifically targets complex social engineering tactics, which now represent up to 80% of all scam-related losses.\n\nThe solution uses a lightweight version of Google’s Gemma model, fine-tuned on local scam conversations to distinguish between benign chatter and manipulative intent. Unlike traditional cloud-based scanning, this model runs directly on smartphones, preserving user privacy by keeping conversation data on the device. It employs a two-stage pipeline: a low-power classifier screens messages, followed by a deeper contextual analysis by the Gemma model to confirm threats and trigger real-time warnings.\n\nThe project was presented at Singapore International Cyber Week (SICW 2026) and emphasizes strict governance, including training within a sovereign sandbox and excluding personally identifiable information. The initiative aims to provide a template for other messaging platforms and operating system vendors to integrate local safety features without compromising end-to-end encryption.","keyPoints":["Scams cause over S$4 billion in losses in Singapore since 2019, with social engineering driving 80% of losses.","The tool uses a fine-tuned Gemma model running on-device to detect scams while preserving privacy.","Development involved a two-stage pipeline and strict governance, excluding private data from training."],"whyItMatters":"This project demonstrates a viable method for integrating privacy-preserving AI safety features into consumer devices, offering a scalable model for governments and tech companies to combat digital fraud without compromising user data.","category":{"slug":"policy","name":"Policy & Regulation","url":"https://digestai.news/category/policy"},"entities":{"companies":["Google DeepMind","GovTech","Singapore Government"],"models":["Gemma"],"people":[]},"firstPublishedAt":"2026-10-14T02:00:14Z","updatedAt":"2026-10-14T02:00:14Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"Google DeepMind","title":"Google DeepMind and Singapore Government announce new AI tool to protect citizens against scams","url":"https://deepmind.google/blog/on-device-ai-scam-detection-mddi","publishedAt":"2026-10-14T02:00:14Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Google DeepMind and Singapore launch on-device scam detection tool\", 14 October 2026, https://digestai.news/story/google-deepmind-and-singapore-launch-on-device-scam-detection-tool","publisher":"Digest AI","title":"Google DeepMind and Singapore launch on-device scam detection tool","datePublished":"2026-10-14T02:00:14Z","url":"https://digestai.news/story/google-deepmind-and-singapore-launch-on-device-scam-detection-tool"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}