DF2023: The Digital Forensics 2023 Dataset for Image Forgery Detection
This dataset addresses the societal danger of image manipulation in online social networks by providing a resource for the research community, though it is incremental as it builds on existing forgery detection efforts.
The authors tackled the problem of detecting manipulated images by releasing the Digital Forensics 2023 dataset, which includes one million images across four forgery categories to enable objective comparison of network architectures and reduce dataset preparation time for researchers.
The deliberate manipulation of public opinion, especially through altered images, which are frequently disseminated through online social networks, poses a significant danger to society. To fight this issue on a technical level we support the research community by releasing the Digital Forensics 2023 (DF2023) training and validation dataset, comprising one million images from four major forgery categories: splicing, copy-move, enhancement and removal. This dataset enables an objective comparison of network architectures and can significantly reduce the time and effort of researchers preparing datasets.