Combating Digitally Altered Images: Deepfake Detection
This addresses the challenge of identifying manipulated images for the public and authorities, but it appears incremental as it builds on existing methods with dataset-specific improvements.
The study tackled the problem of detecting Deepfake images by developing a modified Vision Transformer model, achieving state-of-the-art results on a test dataset.
The rise of Deepfake technology to generate hyper-realistic manipulated images and videos poses a significant challenge to the public and relevant authorities. This study presents a robust Deepfake detection based on a modified Vision Transformer(ViT) model, trained to distinguish between real and Deepfake images. The model has been trained on a subset of the OpenForensics Dataset with multiple augmentation techniques to increase robustness for diverse image manipulations. The class imbalance issues are handled by oversampling and a train-validation split of the dataset in a stratified manner. Performance is evaluated using the accuracy metric on the training and testing datasets, followed by a prediction score on a random image of people, irrespective of their realness. The model demonstrates state-of-the-art results on the test dataset to meticulously detect Deepfake images.