SINGAPORE: Google DeepMind and the Singapore Government are developing a first-of-its-kind on-device scam detection model that alerts Android users in real time to potential scam attempts.
The artificial intelligence model promises to protect users from known scams without allowing any personal data to leave their devices.
The collaboration with the Government Technology Agency of Singapore (GovTech) was announced on the sidelines of the Singapore International Cyber Week on Oct 14.
Mark Chen, director of trust and safety at GovTech, said: “Fighting scams shouldn’t mean sacrificing personal privacy. Working with Google DeepMind, we’re bringing advanced AI protection directly onto citizens’ devices.
“This allows us to catch highly targeted, local scam attempts in real time while keeping personal communications private.”
Under the hood, the safety system is also trained to understand local context. The AI model analyses text exchanges on messaging apps such as WhatsApp and Telegram in real time and is fine-tuned specifically to detect local scam patterns, including those involving the impersonation of government officials and banks.
A release date has not been announced. It is also unclear whether the model will be a default feature of the Android operating system.
The model will also be continuously trained on emerging scam tactics to ensure that it can accurately distinguish between harmless chatter and manipulation tactics used in scams, Google said in a statement on Oct 14.
It added that the AI analyses conversations in messaging apps directly on users’ devices, instead of sending data to external cloud servers, allowing for quicker alerts while ensuring that data remains private.
As part of the initial development process, the model was trained on anonymised datasets from scam reports and intelligence feeds and stress-tested against synthetic conversations made to reflect local speech patterns.
“When deployed, the model will be able to access only on-device conversations with the user’s consent,” Google DeepMind said in a blog post on Oct 14.
“As the model runs entirely on-device, neither the Singapore Government nor Google will be able to access users’ conversations through its deployment,” said Google DeepMind Applied AI director JJ Geewax and group product manager Miguel de Andres, the blog’s authors.
“The project demonstrates how AI can help counter criminality without compromising safety or privacy. It also shows how governments and model providers can work together to build tech for (the) public good,” they said, adding that generic AI models often struggle to identify scam tactics specific to Singapore.
“With this lightweight, on-device model, we’ve proven the ability for local, real-time scam detection while ensuring chat interactions remain secure. We look forward to sharing more soon about our collaboration with the Singapore Government, as well as exploring the potential for similar technology to be deployed in other countries.”
A real-time warning will be triggered on the user’s device when the AI model detects manipulative conversational patterns. The warning will caution users against sharing any sensitive information or transferring funds.
Singapore has lost more than S$4 billion (US$3.1 billion) to scams since 2019. In the first six months of 2026, S$410.6 million was lost to scammers. E-commerce, phishing, investment, job and government official impersonation scams were the most common scam types.
On Oct 14, Google also announced that it would give the Government access to its most advanced AI cybersecurity tools to help cyber defenders find, verify and fix vulnerabilities in minutes.
“By proactively patching weaknesses ahead of time, the program aims to protect essential systems and services from operational disruption and cybersecurity threats,” Google said.
The partnership aligns with the Government’s continued calls for cyber defenders to use AI to fight threats posed by the technology.
Earlier in July, ChatGPT maker OpenAI disclosed that its AI agents had escaped their testing environment and breached the AI software repository Hugging Face to complete a task they had been given.
Other similar incidents have also emerged, including the breach of an Australian healthcare database by a rogue OpenAI bot in June, which Australian Prime Minister Anthony Albanese revealed in September. - The Straits Times/ANN
