Skip to content

BLIP is a VLP (Vision-Language Pre-training) framework that excels in both vision-language understanding and generation tasks using a multimodal mixture of encoder-decoder model and a novel captioning and filtering method for handling noisy data. In this project, we will try to use BLIP in deepfake detection

Notifications You must be signed in to change notification settings

emirhanbilgic/Emirhans_Method_Deepfake

Repository files navigation

Emirhan's Method for Deepfake Detection

Introduction

BLIP is a Vision-Language Pre-training (VLP) framework known for its proficiency in both vision-language understanding and generation tasks. It utilizes a multimodal mixture of encoder-decoder models, along with a novel captioning and filtering method for managing noisy data. In this project, we employ BLIP to detect deepfake content effectively.

Dataset

The dataset utilized in this project includes 300 randomly selected examples from the FF++ dataset. It comprises:

  • 150 Deepfake examples
  • 150 Real examples

These examples are selected from 50 different videos, with each video contributing 3 frames to the dataset. You can access the dataset at this Kaggle link.

Running the Code

Follow these steps to run the code:

  1. Clone the repository.
  2. Download the dataset from the provided link.
  3. Execute the script by running the following command in your terminal:
    python3 script.py /path/to/your/dataset
    

Results

The logs of the testing process can be seen via logs_for_fakes.txt and logs_for_reals.txt files.

  • Accuracy on DeepFakes: 58%
    • True Positives: 29
    • False Positives: 21
  • Accuracy on Real Images: 62%
    • True Negatives: 31
    • False Negatives: 19
  • Overall Accuracy: 60%
    • Total Correct: 60
    • Total Incorrect: 40

About

BLIP is a VLP (Vision-Language Pre-training) framework that excels in both vision-language understanding and generation tasks using a multimodal mixture of encoder-decoder model and a novel captioning and filtering method for handling noisy data. In this project, we will try to use BLIP in deepfake detection

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages