obsTR/Sherlock

Multi modal deepfake detection system using FastAPI, PyTorch, and a Cloudflare Workers edge gateway, with a Next.js dashboard.

18
/ 100
Experimental

This system helps cybersecurity professionals and content moderators detect manipulated media, often called deepfakes. You input a video file, and it outputs a verdict on whether the video's visuals or audio have been synthetically altered, along with confidence scores. It's designed for security analysts, social media platforms, or anyone needing to verify the authenticity of video content.

Use this if you need to quickly and reliably determine if a video's visual or audio components have been faked or manipulated.

Not ideal if you only need to analyze static images or pure audio files, as this system is built for comprehensive video analysis.

cybersecurity content-moderation fraud-detection media-verification digital-forensics
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 3 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

TypeScript

License

Last pushed

Feb 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/obsTR/Sherlock"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.