Inclusion 2024 Global Multimedia Deepfake Detection Challenge: Towards Multi-dimensional Face Forgery Detection

TL;DR

This paper reports on the Inclusion 2024 Global Multimedia Deepfake Detection Challenge, highlighting innovative solutions from top teams to advance multi-dimensional face forgery detection in images and videos.

Contribution

It introduces a large-scale international challenge with novel detection solutions, fostering progress in multimedia deepfake detection research.

Findings

Top teams developed advanced detection algorithms

Challenge attracted 1500 teams and 5000 submissions

Solutions aim to enhance next-generation deepfake detection systems

Abstract

In this paper, we present the Global Multimedia Deepfake Detection held concurrently with the Inclusion 2024. Our Multimedia Deepfake Detection aims to detect automatic image and audio-video manipulations including but not limited to editing, synthesis, generation, Photoshop,etc. Our challenge has attracted 1500 teams from all over the world, with about 5000 valid result submission counts. We invite the top 20 teams to present their solutions to the challenge, from which the top 3 teams are awarded prizes in the grand finale. In this paper, we present the solutions from the top 3 teams of the two tracks, to boost the research work in the field of image and audio-video forgery detection. The methodologies developed through the challenge will contribute to the development of next-generation deepfake detection systems and we encourage participants to open source their methods.