Detecting Digital Image Forgeries with Copy-Move and Splicing Image Analysis using Deep Learning Techniques

Abstract

The proliferation of digitally altered images across social media platforms has escalated the urgency for robust image forgery detection systems. Traditional detection methodologies, while varied, often fall short in addressing the multifaceted nature of image forgeries in the digital landscape. Recognizing the need for advanced solutions, this paper introduces a novel deep-learning approach that leverages the architectural strengths of GNNs, CNNs, VGG16, MobileNet, and ResNet50. Our method uniquely integrates these architectures to effectively detect and analyze multiple types of image forgeries, including image splicing and copy-move forgeries. This approach is groundbreaking as it adapts these networks to focus on identifying discrepancies in the compression quality between forged and original image regions. By examining the differences between the original and compressed image versions, our model constructs a feature-rich representation, which is then analyzed by a tailored deep-learning network. This network has been enhanced by removing its original classifier and implementing a new one specifically designed for binary forgery classification. Very few researchers have explored the application of deep learning techniques in copy-move and splice image analysis for detecting digital image forgeries, making our work particularly significant. A comprehensive comparative analysis with pre-trained models underscores the superiority of our method, with the GNN model achieving an impressive accuracy of 98.54 percent on the CASIA V1 dataset. This not only sets a new benchmark in the field but also highlights the efficiency of our model, which benefits from reduced training parameters and accelerated training times.