BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization

Abstract

We introduce a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet. Unlike previous eorts, BusterNet is a pure, end-to-end trainable, deep neural network solution. It features a two-branch architecture followed by a fu- sion module. The two branches localize potential manipulation regions (by looking for visual artifacts) and copy-move regions (by assessing vi- sual similarities), respectively. To the best of our knowledge, this is the rst CMFD algorithm with discernibility to localize source/target re- gions.We also propose simple schemes for synthesizing large-scale CMFD samples using out-of-domain datasets, and stage-wise strategies for eec- tive BusterNet training. Our extensive studies demonstrate that Buster- Net outperforms state-of-the-art copy-move detection algorithms by a large margin on the two publicly available datasets, CASIA and CoMo- FoD, and that it is robust against various known attacks.