Abstract
The rapid advancement of artificial intelligence (AI) has led to the emergence of several technologies, including Generative Adversarial Networks (GANs), deepfakes, generative AI, CGI, and anti-forensics techniques. These technologies pose a significant threat to the trustworthiness of media content. To detect unintentional misinformation or deliberate deception through disinformation and to ensure trust and authentication in digital content, we offer a comprehensive evaluation platform known as the Open Media Forensic Challenge (OpenMFC), accessible at
https://mfc.nist.gov. This platform is designed to enable public researchers to develop media forensic technologies for the automatic detection of inauthentic imagery, such as images and videos, and to trace their digital content origins. The OpenMFC is an online evaluation series open to participants from around the world. It aims to support and promote research in media forensics and advance state-of-the-art technologies. The initiative builds upon the efforts of the NIST Media Forensics Challenge (MFC) and its support for the DARPA MediFor Program (2017-2020). During this presentation, we will provide an overview of the OpenMFC program. This overview will include details on program design, major challenges, evaluation tasks, released datasets, past years' evaluation reports, and our future evaluation plans. We will also share our vision and outline plans for future developments in this field, along with a desire to collaborate with other teams and organizations.