Saved in:
Bibliographic Details
Main Authors: Chen, Pengzhen, Liu, Yanwei, Gu, Xiaoyan, Chen, Xiaojun, Liu, Wu, Wang, Weiping
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.17531
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912972591333376
author Chen, Pengzhen
Liu, Yanwei
Gu, Xiaoyan
Chen, Xiaojun
Liu, Wu
Wang, Weiping
author_facet Chen, Pengzhen
Liu, Yanwei
Gu, Xiaoyan
Chen, Xiaojun
Liu, Wu
Wang, Weiping
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17531
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
Chen, Pengzhen
Liu, Yanwei
Gu, Xiaoyan
Chen, Xiaojun
Liu, Wu
Wang, Weiping
Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
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.
title Rel-Zero: Harnessing Patch-Pair Invariance for Robust Zero-Watermarking Against AI Editing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2603.17531