Google DeepMind, GovTech Singapore jointly develop on-device model to flag chat scams. Google DeepMind and the Government Technology Agency of Singapore (GovTech) have developed a scam-detection model that runs on smartphones and analyzes conversations without sending message content to external servers. In a statement on Wednesday, Google DeepMind said the project forms part of Google's National AI Partnership with the Singapore government. Scams account for more than half of Singapore's reported crimes, and losses exceeded S$4 billion since 2019. Social engineering, in which attackers build trust through convincing conversations before asking for money, now accounts for up to 80 percent of those losses. The model is based on Google's lightweight Gemma model, which the partners fine-tuned on local scam conversations. The training material covered impersonation of public institutions, banks and local figures, along with emerging regional schemes. The model works in two stages. A lightweight classifier screens incoming messages at low power cost and flags suspicious ones. The fine-tuned Gemma model then analyzes a larger slice of the conversation to confirm a manipulative pattern or dismiss a false alarm. When it confirms a threat, it displays a real-time warning on the device, advising the user to pause before sharing information or money. The partners said the model can access conversations only with user consent and in line with each application's terms of use. Neither the government nor Google can read conversations through its deployment. Google said the rollout will be phased and developed with the Singapore government. The model would be integrated into applications used by citizens. Fine-tuning took place in a GovTech-managed cloud environment, with training data kept separate. The partners said training excluded private and personally identifiable information, using anonymized data from scam reports and intelligence feeds. Google DeepMind said the model was tested against synthetic dialogues and local language patterns across several scam categories.

GovTech and Google DeepMind build privacy-first AI to counter Singapore Scams. October 15, 2026 How do you feel about this story? Express Your Reaction Google DeepMind and the Government Technology Agency of Singapore (GovTech) announced on October 14, 2026, at Singapore International Cyber Week, an AI model that detects scam conversations directly on smartphones without sending messages to the cloud. The project targets social engineering scams, which account for most scam losses, while keeping users' personal communications private. Key facts at A glance. * Google DeepMind and GovTech announced the on-device scam detection model on October 14, 2026. * The model is built on Google's lightweight Gemma model and fine-tuned on local scam conversations. * Detection runs in two stages: a fast screening classifier, followed by deeper analysis from the fine-tuned Gemma model. * Conversations are processed on the device, and neither Google nor the Singapore Government can access them. * Training used anonymised scam reports and intelligence feeds and excluded personally identifiable information. * Scams account for more than half of Singapore's reported crimes, with losses exceeding $4 billion since 2019. * No rollout date or participating applications have been announced. A locally trained model built for privacy. Google DeepMind and GovTech have developed an AI model that identifies manipulative patterns in smartphone conversations and warns users before they share sensitive information or transfer money. The model was presented at Singapore International Cyber Week 2026 and forms part of Google's National AI Partnership with the Singapore Government. The system is built on Gemma, Google's lightweight open model. It was fine-tuned on local scam conversations involving impersonation of public institutions, banks and local figures, as well as emerging regional schemes. The model is intended for Android devices and will be updated as scam methods change. The project responds to the scale of fraud in Singapore. Scams make up more than half of the country's reported crimes, and losses have exceeded S$4 billion since 2019. Google DeepMind said social engineering, where scammers use convincing conversations to manipulate victims, now accounts for up to 80 percent of scam losses. How the two-stage detection works. To limit battery use, the system screens messages in two stages. A lightweight classifier first checks incoming messages for potential threats. When it flags suspicious content, the fine-tuned Gemma model reviews a larger portion of the conversation to confirm the threat or rule out a false alarm. If manipulative patterns are confirmed, the user receives a real-time warning advising caution. Because analysis happens on the phone itself, messages are not sent to external servers. Mark Chen, Director of Trust and Safety at GovTech, said fighting scams "shouldn't mean sacrificing personal privacy." He added that the approach is designed to catch targeted local scams while keeping communications private. Training safeguards and rollout plans. The teams fine-tuned the model in a Google Cloud environment managed by GovTech, keeping training data isolated. They used anonymised datasets drawn from scam reports and intelligence feeds and excluded private and personally identifiable information. The model was tested against synthetic conversations and local datasets covering a range of scam types and impersonation tactics. The two organisations plan to introduce the model gradually through applications developed with the Singapore Government. Once deployed, it will access conversations only with user consent and under each application's terms of use. Google also released Be Scam Ready 2.0, a shorter version of its scam awareness game, as part of the same announcement. Publicly available information remains limited. No rollout date, participating applications or performance figures have been disclosed. Google DeepMind said it is exploring whether similar technology could be deployed in other countries. Editorial research note. This report synthesizes recent reporting and publicly available financial and regulatory information. The perspectives presented reflect neutral newsroom-style reporting.

Google is working with Singapore on cyber defence and scam detection, including its Fairwind program and an Android scam-detection model that analyses conversations on the device rather than in the cloud. Under Fairwind, cyber defenders will get access to Google tools including Gemini 4 Argon and CodeMender to find and patch software vulnerabilities. Separately, Google DeepMind and the Government Technology Agency of Singapore (GovTech Singapore) are developing the Android scam-detection model.