Enhancing copy-move forgery detection through a novel CNN architecture and comprehensive dataset analysis

In the contemporary digital era, images are omnipresent, serving as pivotal entities in conveying information, authenticating experiences, and substantiating facts. The ubiquity of image editing tools has precipitated a surge in image forgeries, notably through copy-move attacks where a portion of an image is copied and pasted within the same image to concoct deceptive narratives. This phenomenon is particularly perturbing considering the pivotal role images play in legal, journalistic, and scientific domains, necessitating robust forgery detection mechanisms to uphold image integrity and veracity. While advancements in Convolutional Neural Networks (CNN) have propelled copy-move forgery detection, existing methodologies grapple with limitations concerning the detection efficacy amidst complex manipulations and varied dataset characteristics. Additionally, a palpable void exists in comprehensively understanding and exploiting dataset heterogeneity to enhance detection capabilities. This heralds a pronounced exigency for innovative CNN architectures and nuanced understandings of dataset intricacies to augment detection capabilities, which has remained notably underexplored in the prevailing literature. Against this backdrop, our research broaches novel frontiers in copy-move forgery detection by introducing an innovative CNN architecture meticulously tailored to discern the subtlest manipulations, even amidst intricate image contexts. An extensive analysis of multiple datasets – MICC-F220, MICC-F600, and a combined variant – enables us to delineate a granular understanding of their attributes, thereby shedding unprecedented light on their influences on detection performance. Further, our research goes beyond mere detection, delving deep into comprehensive analyses of varied datasets and conducting additional experiments with differential training-validation sets and randomly labeled data to scrutinize the robustness and reliability of our model. We not only meticulously document and analyze our findings but also juxtapose them against extant models, offering an exhaustive comparative analysis.