# Deepfake Detection and Generation Challenge — Data

来源：https://www.kaggle.com/competitions/Deepfake_Detection_and_Generation_Challenge_Red_Team/data

采集时间：2026-10-24T15:47:19Z

As stated in the guideline, the FaceForensics++ dataset can be freely used for model training and internal testing (refer to the guideline and the GitHub link below).  
- FaceForensics++ dataset (Github): https://github.com/ondyari/FaceForensics

Please generate and submit manipulated video data based on the 590 face data files provided in the Data section.
You are free to apply any manipulation techniques of your choice.
Along with the manipulated video data, you must upload a submission.csv file.
(Please refer to the provided **sample_submission.csv** file for the required format.)


![](assets/91a9bd4c18aea46847d1f626.jpg)



- **Original**: Name of the original video file

- **Target**: Name of the target video file whose face is to be manipulated

- **Manipulation**: Name of the manipulated video file

- **Description**: Description of the manipulation method used