The Global Multimedia Deepfake Detection Challenge 2024 officially announced

On July 1, The Global Multimedia Deepfake Detection Challenge 2024 (The Challenge) officially launched. This competition is co-hosted by the INCLUSION•Conference on the Bund and Ant Group, and organized by Ant Digital Technologies, with a total prize pool of 1,000,000 RMB (around $137,000).

The Challenge aims to invite participants to develop, test, and further evolve more accurate, effective, and innovative detection models against various types of Deepfake attacks in real-world scenarios, as well as to motivate innovative defense strategies and improve Deepfake recognition accuracy.

The Challenge is structured into two tracks: an image track and an audio/video track, featuring datasets with multi-dimensional face forgery methods. The comprehensive training dataset comprises over 1 million samples. Participants are tasked with developing AI models that can predict the probability of a deepfake instance. The 20 models demonstrating the highest accuracy will advance to the final round. During the final stage, a panel of experts will evaluate the top teams against criteria including accuracy, generalizability, innovation, practical applicability, and the interpretability of their solutions. The top three teams from each track will receive an invitation to the 2024 INCLUSION•Conference on the Bund in Shanghai, where they will be honored at an award ceremony and compete in an exhibition match.

Renowned industry organizations and companies will collaborate to co-organize the challenge. Key partners include the Advanced Technology Exploration Community (ATEC), the Cybersecurity College of the University of Science and Technology of China, and Ant Security Lab. ZOLOZ will contribute technical support, while Alibaba Cloud will offer the necessary computing power support.