Abstract
The development of powerful deep learning technologies has brought about some negative effects to both society and individuals. One such issue is the emergence of fake media. To tackle the issue, we have organized the Trusted Media Challenge (TMC) to explore how Artificial Intelligence (AI) technologies could be leveraged to combat fake media. Together with the challenge, we have released a challenge dataset which consists of 4,380 fake and 2,563 real videos. All these videos are accompanied with audios and different video and/or audio manipulation methods are adopted to produce different types of fake media. The videos in the dataset have various durations, background, illumination, a minimum resolution of 360p and may contain perturbations that mimic transmission errors and bad compression. We have also carried out a user study to demonstrate the quality of our composed dataset. The results show that our dataset has a promising quality and can fool human participants in many cases.
Abstract (translated)
URL
https://arxiv.org/abs/2201.04788
