Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling

TL;DR

ReImage is a neural watermarking framework that enables robust image self-recovery from tampering by embedding a shuffled version of the image as a watermark, achieving high-quality restoration across various attack scenarios.

Contribution

The paper introduces ReImage, a novel neural watermarking method with pixel shuffling for effective image self-recovery, addressing limitations of existing techniques.

Findings

Achieves state-of-the-art recovery quality in tampering scenarios

Effectively reconstructs original images from manipulated versions

Demonstrates robustness across diverse tampering attacks

Abstract

The rapid growth of Artificial Intelligence-Generated Content (AIGC) raises concerns about the authenticity of digital media. In this context, image self-recovery, reconstructing original content from its manipulated version, offers a practical solution for understanding the attacker's intent and restoring trustworthy data. However, existing methods often fail to accurately recover tampered regions, falling short of the primary goal of self-recovery. To address this challenge, we propose ReImage, a neural watermarking-based self-recovery framework that embeds a shuffled version of the target image into itself as a watermark. We design a generator that produces watermarks optimized for neural watermarking and introduce an image enhancement module to refine the recovered image. We further analyze and resolve key limitations of shuffled watermarking, enabling its effective use in self-recovery. We demonstrate that ReImage achieves state-of-the-art performance across diverse tampering scenarios, consistently producing high-quality recovered images. The code and pretrained models will be released upon publication.