Image Protection for Robust Cropping Localization and Recovery

Existing image cropping detection schemes ignore that recovering the cropped-out contents can unveil the purpose of the behaved cropping attack. This paper presents $\mathbf{\text{CLR}}$-Net, a novel image protection scheme addressing the combined challenge of image $\mathbf{\text{C}}$ropping $\mathbf{\text{L}}$ocalization and $\mathbf{\text{R}}$ecovery. We first protect the original image by introducing imperceptible perturbations. Then, typical image post-processing attacks are simulated to erode the protected image. On the recipient’s side, we predict the cropping mask and recover the original image. Besides, we propose a novel $\mathbf{\text{F}}$ine-$\mathbf{\text{G}}$rained generative $\mathbf{\text{JPEG}}$ simulator (FG-JPEG) as well as a feature alignment network to improve the real-world robustness. Comprehensive experiments prove that the quality of the recovered image and the accuracy of crop localization are both satisfactory.