UGAD: Universal Generative AI Detector utilizing Frequency Fingerprints
This addresses the critical need to discern real from fake images for security and media integrity, though it appears incremental as it builds on existing detection approaches.
The study tackled the problem of detecting AI-generated images, such as those from Diffusion models, by introducing UGAD, a multi-modal method that improved accuracy by 12.64% and AUC by 28.43% compared to existing state-of-the-art methods.
In the wake of a fabricated explosion image at the Pentagon, an ability to discern real images from fake counterparts has never been more critical. Our study introduces a novel multi-modal approach to detect AI-generated images amidst the proliferation of new generation methods such as Diffusion models. Our method, UGAD, encompasses three key detection steps: First, we transform the RGB images into YCbCr channels and apply an Integral Radial Operation to emphasize salient radial features. Secondly, the Spatial Fourier Extraction operation is used for a spatial shift, utilizing a pre-trained deep learning network for optimal feature extraction. Finally, the deep neural network classification stage processes the data through dense layers using softmax for classification. Our approach significantly enhances the accuracy of differentiating between real and AI-generated images, as evidenced by a 12.64% increase in accuracy and 28.43% increase in AUC compared to existing state-of-the-art methods.