FLORIDA: Fake-looking Real Images Dataset
This addresses a gap in deepfake detection for images that are real but appear artificial, though it is incremental as it focuses on dataset creation and initial testing.
The researchers tackled the problem of whether AI models can accurately identify genuine images that look fake by creating a dataset of 510 such images and testing two models, which performed poorly on it.
Although extensive research has been carried out to evaluate the effectiveness of AI tools and models in detecting deep fakes, the question remains unanswered regarding whether these models can accurately identify genuine images that appear artificial. In this study, as an initial step towards addressing this issue, we have curated a dataset of 510 genuine images that exhibit a fake appearance and conducted an assessment using two AI models. We show that two models exhibited subpar performance when applied to our dataset. Additionally, our dataset can serve as a valuable tool for assessing the ability of deep learning models to comprehend complex visual stimuli. We anticipate that this research will stimulate further discussions and investigations in this area. Our dataset is accessible at https://github.com/aliborji/FLORIDA.