AURA
Phishing and fraud detector that keeps learning from analyst feedback. A FastAPI backend handles inference, drift monitoring, a hot-swap model registry and online retraining; a Chrome extension delivers real-time verdicts inside Gmail; a Next.js analyst dashboard manages the review and redeployment cycle — all connected through a PostgreSQL-backed audit trail.
- Python
- FastAPI
- scikit-learn
- PostgreSQL
- Next.js
- TypeScript
- Docker
The problem
Phishing emails reach the inbox, and a detection model that never hears whether it was right slowly goes stale.
What was built
- A FastAPI backend that handles inference, model versioning and online retraining from analyst feedback.
- Drift monitoring, and a hot-swap model registry so a retrained model replaces the live one without downtime.
- A Chrome extension that shows real-time verdicts inside Gmail.
- A Next.js analyst dashboard for the review and redeployment cycle.
- A PostgreSQL-backed audit trail connecting all three.