Enhancing the Generalization of Synthetic Image Detection Models through the Exploration of Features in Deep Detection Models

One of the major challenges of AI is the misuse of images generated by generative models. Advances in this field have reached a point where distinguishing between real and fake images can be impossible for humans and challenging even for machines. Although significant work has been done on detecting fake images, there is an ongoing competition between content generation and detection methods. However, a significant challenge for detection methods is their limitation to content generated by specific models. This study aims to enhance the generalization of fake image detection methods. Experimental results indicate that modifications made to the base model have contributed to improving its generalizability.