Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing

2026-03-18

AI Summary

This work addresses the growing threat posed by AI-based image editing to digital image authenticity, where conventional watermarking compromises visual quality and existing zero-watermarking approaches lack sufficient robustness. The study presents the first non-intrusive zero-watermarking framework that leverages a newly identified invariance: the preserved relational distances between image patch pairs during AI editing. By modeling structural consistency without altering the original image, the proposed method enables reliable content authentication. It integrates diffusion model–based editing analysis, patch-pair relational modeling, and a zero-watermark matching mechanism, achieving superior performance across diverse mainstream AI editing operations. The approach demonstrates both high robustness against manipulations and perfect visual fidelity, offering a practical solution for verifying the integrity of AI-edited images.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Recent advancements in diffusion-based image editing pose a significant threat to the authenticity of digital visual content. Traditional embedding-based watermarking methods often introduce perceptible perturbations to maintain robustness, inevitably compromising visual fidelity. Meanwhile, existing zero-watermarking approaches, typically relying on global image features, struggle to withstand sophisticated manipulations. In this work, we uncover a key observation: while individual image patches undergo substantial alterations during AI-based editing, the relational distance between patch pairs remains relatively invariant. Leveraging this property, we propose Relational Zero-Watermarking (Rel-Zero), a novel framework that requires no modification to the original image but derives a unique zero-watermark from these editing-invariant patch relations. By grounding the watermark in intrinsic structural consistency rather than absolute appearance, Rel-Zero provides a non-invasive yet resilient mechanism for content authentication. Extensive experiments demonstrate that Rel-Zero achieves substantially improved robustness across diverse editing models and manipulations compared to prior zero-watermarking approaches.

Problem

• zero-watermarking
• AI editing
• image authentication
• diffusion-based editing
• robustness

Innovation

• zero-watermarking
• patch-pair invariance
• AI editing robustness
• relational distance
• diffusion-based image editing