Image Protection for Robust Cropping Localization and Recovery

TL;DR

This paper introduces CLR-Net, a novel image protection scheme that enables accurate cropping localization and recovery of original images after typical post-processing attacks, enhancing image security and forensic capabilities.

Contribution

The paper proposes CLR-Net, combining imperceptible perturbations, crop localization, image recovery, and a new FG-JPEG simulator with feature alignment to improve robustness against real-world attacks.

Findings

High-quality image recovery after cropping and attacks

Accurate crop localization in various scenarios

Enhanced robustness with FG-JPEG and feature alignment

Abstract

Existing image cropping detection schemes ignore that recovering the cropped-out contents can unveil the purpose of the behaved cropping attack. This paper presents \textbf{CLR}-Net, a novel image protection scheme addressing the combined challenge of image \textbf{C}ropping \textbf{L}ocalization and \textbf{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 \textbf{F}ine-\textbf{G}rained generative \textbf{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.