1M-Deepfakes Detection Challenge

TL;DR

The 1M-Deepfakes Detection Challenge aims to advance deepfake detection and localization techniques using a large-scale dataset of over 1 million manipulated videos, fostering research in digital media security.

Contribution

This paper introduces a large-scale deepfake detection challenge based on the AV-Deepfake1M dataset, encouraging development of improved detection and localization methods.

Findings

Engages the research community with a large-scale dataset

Provides baseline models and evaluation scripts

Facilitates development of next-generation deepfake detection systems

Abstract

The detection and localization of deepfake content, particularly when small fake segments are seamlessly mixed with real videos, remains a significant challenge in the field of digital media security. Based on the recently released AV-Deepfake1M dataset, which contains more than 1 million manipulated videos across more than 2,000 subjects, we introduce the 1M-Deepfakes Detection Challenge. This challenge is designed to engage the research community in developing advanced methods for detecting and localizing deepfake manipulations within the large-scale high-realistic audio-visual dataset. The participants can access the AV-Deepfake1M dataset and are required to submit their inference results for evaluation across the metrics for detection or localization tasks. The methodologies developed through the challenge will contribute to the development of next-generation deepfake detection and localization systems. Evaluation scripts, baseline models, and accompanying code will be available on https://github.com/ControlNet/AV-Deepfake1M.