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

2025-11-28

AI Summary

To address the challenge of reconstructing original image content after tampering, this paper proposes ReImage—a novel framework that pioneers end-to-end neural watermarking for image self-recovery. ReImage encodes the original image as a pixel-level scrambled self-embedding watermark and introduces a dedicated generator coupled with a deep enhancement module to jointly ensure robust watermark embedding and high-fidelity reconstruction. Unlike conventional watermarks designed solely for tampering detection, ReImage enables semantic-consistent, pixel-accurate restoration of tampered regions. Extensive experiments across diverse tampering scenarios demonstrate that ReImage significantly outperforms state-of-the-art methods in both quantitative recovery accuracy and qualitative visual quality. By unifying authenticity verification with reconstructive capability, ReImage establishes a new paradigm for verifiable and recoverable digital media integrity assessment.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

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.

Problem

• Recovering original images from tampered versions using watermarking
• Addressing inaccurate recovery in existing self-recovery methods
• Enhancing robustness against diverse image tampering scenarios

Innovation

• Neural watermarking embeds shuffled image as watermark
• Generator optimizes watermarks for self-recovery framework
• Image enhancement module refines recovered image quality