ScamBreak
Global scam operations stole >$1 trillion last year, with video call fraud surging 1,500% across APAC.
Core trick
Samples live video-call frames into parallel Gemini agents that score badges, backdrops and coercive speech, returning a verdict within seconds.
Description
Global scam operations stole >$1 trillion last year, with video call fraud surging 1,500% across APAC. Scammers run organized call centers with fake uniforms, staged offices, and counterfeit badges, video-calling victims to threaten arrest in real time. Yet every anti-scam tool works after the damage is done. Nothing protects victims during the call.
ScamBreak changes that. Four Gemini agent swarms work in parallel to analyze live video calls in real time: scanning for fake badges and staged backdrops, detecting psychological manipulation, validating against government protocols, and delivering a verdict within seconds.
When a scam is detected, it intervenes with clear warnings designed for victims under stress. With one click, it auto-generates a complete incident report with AI evidence, screenshots, transcript analysis, and visual identity search, ready to submit to authorities. ScamBreak doesn't detect scams after they happen. It breaks them while they're happening.
README excerpt
# 🛡️ ScamBreak AI ### Real-time AI defense against live video call scams > **Built at the Gemini 3 Singapore Hackathon 2025** | Powered by Google Gemini 2.0 Flash --- ## 🚨 The Problem Global scam operations stole **over $1 trillion in 2024** (GASA). Deepfake and video call fraud surged **1,500% across Asia-Pacific**. In Singapore alone, government impersonation scams caused **S$240M+ in losses** from 3,400+ cases. Today's scammers don't just send phishing texts. They run **organized call centers** with fake police uniforms, staged government offices, and counterfeit badges, calling victims live on video, accusing them of crimes, and demanding immediate money transfers under threat of arrest. **Every anti-scam tool on the market today works *after* the damage is done**: blocking known numbers, flagging suspicious texts, or filing reports post-incident. Nothing protects victims **during** the call itself. ## 💡 The Solution **ScamBreak AI** is the first real-time AI intervention system for live video call scams. The moment a suspicious video call begins, a **swarm of four Gemini-powered AI agents** analyze it simultaneously: | Agent | Role | |-------|------| | 🔍 **Vision Sentinel** | Scans video feed for fake badges, green screens, staged backdrops, and counterfeit documents | | 🧠 **PsyOps Analyzer** | Detects psychological manipulation tactics: fear, urgency, isolation, and coercion patterns | | 📋 **Protocol Validator** | Checks if the caller violates official govern