Skip to main content
  1. Projects/

KYC Liveness & Deepfake Detection

SJ.Wu
Author
SJ.Wu
Backend microservices in production, now also building applied ML / computer vision for identity verification (liveness & deepfake detection). Ex-SSD firmware engineer.
Table of Contents

A production identity-verification service that decides whether a face-verification submission comes from a real, live person — or from a spoof or deepfake.

What it does
#

  • A multi-stage decision pipeline: quality gate → liveness gate → model consensus, returning an accept / review / reject decision with reasons.
  • Combines physical liveness cues (multi-frame RGB light-reaction checks) with an ensemble of deep models for deepfake detection.
  • Served as an HTTP API for synchronous verification.

Tech
#

  • Models — convolutional networks (EfficientNet / Xception / CLIP-based) plus a gradient-boosting model, combined by consensus.
  • Stack — Python, PyTorch, ONNX, FastAPI; end-to-end train → evaluate → deploy pipeline with automated retraining and reporting.
  • Results — multi-model AUC ≥ 0.99 on held-out data; tuned to run within KYC latency budgets on CPU.