Balaji-Kartheek/DeepFake_Detection

Designed and Developed end-to-end scalable Deep Learning Project. It is a detection system trained using InceptionV3(CNN model) + GRU(Sequential model) model to classify a video as Real or Fake. Obtained the test accuracy of 89%.

41
/ 100
Emerging

This project helps identify manipulated videos, known as deepfakes, by analyzing video frames to determine if a person's face has been digitally altered. You input a video file, and the system outputs a classification of whether the video is 'REAL' or 'FAKE'. This is useful for content moderators, journalists, or anyone needing to verify video authenticity on social media or other platforms.

Use this if you need to quickly check if a video might be a deepfake, especially for content where a single face is the primary subject.

Not ideal if your videos contain multiple faces or have dark backgrounds, as the system may struggle with detection in those scenarios.

content-moderation video-verification digital-forensics fake-news-detection
No License No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

67

Forks

19

Language

Jupyter Notebook

License

Last pushed

Dec 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Balaji-Kartheek/DeepFake_Detection"

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