Image splicing forgery detection by combining synthetic adversarial networks and hybrid dense U‐net based on multiple spaces

Abstract

With the popularity of image editing tools, the originality and information security of images are facing serious threats. The most common threat is splicing forgery that copies a part of the area from one donor image to the acceptor one. Some research works were proposed to protect the image originality, whereas they are still difficult to apply in practice.There are two main reasons: (a) very limited data for learning models; (b) huge attribute differences between the donor and acceptor images. We propose two novel tasks to conquer the above challenges: Synthetic Adversarial Networks (SANs) and Hybrid Dense U-Net (HDU-Net). SAN finds the most secluded position for inserting tampered areas in an image by learning the association between scenes and objects, and can enlarge the original small data set by more than 40 times. We call the data set SF-Data generated by SAN. We combine the dense U-Net that detects the differences of the essential attributes of image with four spaces containing more available feature information to propose HDU-Net. Then, the synthetic data set SF-Data are used to train HDU-Net. We perform various attack experiments on several public data sets to demonstrate the effectiveness and robustness of our method.

End-to-end image splicing localization based on multi-scale features and residual refinement module

“…Recently, several methods have been proposed to directly implement pixel-level or region-level forgery localization. Such methods are based on different network structures, such as fully CNNs, faster region convolutional neural network (R-CNN), 15 dual-stream networks, 24 and so on. In Ref.…”

“…Li and Chen et al 14 achieved pixel-level localization prediction by feature enhancement on both RGB streams and noise streams using spatial attention and channel attention. Yang et al 15 adopted multiple dense U-Net networks to detect features from multiple domains and determined the presence of splicing tampering operations by use of the features from different domains. However, in the prediction of the localization map, some actual regions will be mistaken as tampered regions.…”