Loading
Loading
We use strictly necessary cookies to run this site, and analytics cookies to understand how it's used. See our Privacy Policy for details.
On-device AI scam detection developed by Google DeepMind and GovTech Singapore uses a fine-tuned Gemma model to analyze suspicious conversations entirely on a user's smartphone, with no message content transmitted to external servers.
Summary
Unveiled at Singapore International Cyber Week 2026, the privacy-preserving system uses Sovereign Sandbox training on local scam data to catch social engineering patterns generic classifiers miss.
This is a brief wire summary, the full story (linked below) has the complete details.
KazaSec's take
Most public cloud incidents trace back to a misconfiguration, an overly permissive IAM role, a storage bucket left open, a default setting nobody revisited, rather than a flaw in the cloud provider itself. A cloud security review is built to catch exactly that class of mistake before it's found the hard way.
Coverage details
We've archived 198 other articles touching the same topic (security) , see the full security news archive.
Related security advisories
Relevant from KazaSec
More coverage on this topic
We help organizations find and fix the gaps before they make headlines.