Shallow- and Deep- fake Image Manipulation Localization Using Deep Learning

Forged image localization is an important research task, as such images may have a tremendous impact of various aspects of society. Images can be manipulated using image editing tools (known as “shallowfakes”) or, recently, artificial intelligence techniques (“deepfakes”). While there are many existing works that are designed for manipulated areas localization on either shallow- or deep-fake images, there is no single solution that works for both cases. In this paper, we propose the first solution that can perform the localization task on both shallow- and deep-fake images, with high inference accuracy. The dataset and code are available at: https://github.com/zjbthomas/ShallowDeepFakesLocalization.