Google DeepMind, GovTech developing first-of-its-kind scam detection AI model for Android users
Google DeepMind and Singapore's Government Technology Agency (GovTech) are collaborating to create a unique on-device scam detection model for Android users. According to Mark Chen, director of trust and safety at GovTech, this AI model will alert users in real-time about potential scam attempts without sacrificing their privacy.
The AI model, which is currently in the development stage, will analyze text exchanges on messaging apps like WhatsApp and Telegram to detect local scam patterns, including the impersonation of government officials and banks. It will be trained on anonymized datasets of scam reports and stress-tested against synthetic conversations reflecting local speech patterns.
Once deployed, the model will only access on-device conversations with user consent, ensuring that neither the government nor Google can access users' conversations. The model's release date has not been announced, and it is unclear if it will become a default feature in Android operating systems. The partnership aims to demonstrate how AI can protect against criminal activity while maintaining privacy, and Google also plans to share its advanced AI cybersecurity tools with the government to help identify and fix vulnerabilities.
Written by urgent.news from Straits Times's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
