Show HN：VeridisQuo – 具備可解釋 AI 的開源深度偽造偵測器

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

To see all available qualifiers, see our documentation.

Model and application for deepfake detection using a hybrid approach (spatial + frequency-based)

License

Uh oh!

There was an error while loading. Please reload this page.

VeridisQuo-orga/VeridisQuo

Folders and files

Latest commit

History

Repository files navigation

VeridisQuo

Where is the truth?

A state-of-the-art neural network designed to detect deepfake videos and highlight the altered areas in each frame using explainable AI.

Result

Pipeline

Model Architecture

Hybrid Detection System

Model Specifications

Training

Infrastructure

We trained the model on an RTX 3090 (with CUDA) for approximately 4 hours.
We used the GPU provider vast.ai

The training file is located in the training/trainer.py module

Dataset

Source

We started from an existing dataset found on Kaggle:
FaceForensics++ Dataset (C23)

Containing 7000 videos with numerous deepfake techniques:

We extracted the frames and faces from these videos to create our dataset:
VeridisQuo Preprocessed Dataset

Preprocessing Pipeline

The dataset was built using the following pipeline:

Distribution

Total: 716,438 images

Configuration & Results

Configuration

Results

Training Accuracy

Training Loss

API Reference

Endpoints

Request Format (POST /api/v1/analyze)

Parameters:

Response Format

Quick Start

Prerequisites

Clone project

Launch backend

server runs on http://localhost:8000 | Docs at /docs

Launch frontend

Development server on http://localhost:3000

Citation

If you use VeridisQuo in your research, please cite:

About

Model and application for deepfake detection using a hybrid approach (spatial + frequency-based)

Topics

Resources

License

Uh oh!

There was an error while loading. Please reload this page.

Stars

Watchers

Forks

Releases

  1

Uh oh!

There was an error while loading. Please reload this page.

Contributors

  2

Languages

Footer

Footer navigation