Forensic Analysis of Synthetically Generated Western Blot Images

The widespread diffusion of synthetically generated content is a serious threat that needs urgent countermeasures. As matter fact, the generation synthetic not restricted to multimedia data like videos, photographs or audio sequences, but covers significantly vast area can include biological images as well, such western blot and microscopic images. In this paper, we focus on detection These are largely explored in biomedical literature it has been already shown they be easily counterfeited with few hopes spot manipulations by visual inspection using standard forensics detectors. To overcome absence publicly available for task, create new dataset comprising more than 14K original 24K images, four different state-of-the-art methods.We investigate strategies detect blots, exploring binary classification methods well one-class both scenarios, never exploit at training stage. achieved results show good accuracy, even though exploited detectors optimized over versions these scientific We also test robustness developed against post-processing operations commonly performed showing robust JPEG compression some generative models recognizable, despite application editing might alter artifacts leave.