Robust Yet Imperceptible Diffusion Watermarking For AI-Generated Image Verification

计算机科学 数字水印 计算机视觉 人工智能 稳健性(进化) 图像(数学) 噪音(视频) 图像处理 模式识别(心理学) 图像分割 特征提取 扩散 复制保护 变换编码 离散余弦变换 可视化 各项异性扩散 算法 方案(数学)
作者
Shuren Qi,Wenying Wen,Mengxin Shen,Yushu Zhang,FengLei Fan
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:: 1-13
标识
DOI:10.1109/tmm.2026.3734777
摘要

Diffusion models have enabled highly realistic image generation, but their misuse also raises growing concerns about misleading visual content. Digital watermarking has emerged as a promising proactive solution for verifying AI-generated images in cooperative deployment settings. An effective watermarking method for diffusion models should ideally satisfy two key properties: imperceptibility and robustness. However, existing methods still face a clear trade-off between them: pixel-level approaches usually preserve image fidelity well but are vulnerable to regeneration-based removal, whereas content-level approaches are often more robust but may compromise reproducibility, pixel-level consistency, or deployment efficiency due to retraining. In this paper, we revisit diffusion watermarking from the perspective of embedding space design. We argue that a major difficulty lies in finding an embedding space that simultaneously captures components that are both visually insensitive and stable under common distortions. To address this issue, we propose a plug-and-play watermarking framework that embeds watermark information into the circular harmonic expansion of the initial noise in diffusion models. This embedding space provides two favorable properties for watermarking: amplitude-based invariance, which supports reliable detection under geometric transformations, and reconstructability with frequency selectivity, which helps preserve the original generation behavior while limiting perceptual distortion. Extensive experiments demonstrate that the proposed method achieves a strong robustness-imperceptibility trade-off without retraining the diffusion model. In particular, it shows strong robustness against natural distortions, geometric transformations, and regeneration-based expert attacks, while substantially improving imperceptibility over representative content-level baselines. Moreover, the method remains lightweight and broadly compatible with existing diffusion-model pipelines, making it practical for active AI-generated image verification.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
平常的傲旋完成签到 ,获得积分10
刚刚
哈哈哈完成签到,获得积分10
1秒前
Eric发布了新的文献求助10
1秒前
zchhh完成签到 ,获得积分10
2秒前
花样年华发布了新的文献求助10
2秒前
隋玉发布了新的文献求助10
2秒前
2秒前
谨慎枫叶发布了新的文献求助10
3秒前
4秒前
神宝嘎li发布了新的文献求助10
4秒前
英俊的铭的应助被小王采纳,获得10
4秒前
孝择发布了新的文献求助10
4秒前
海边捡贝壳完成签到 ,获得积分10
4秒前
科研小郭发布了新的文献求助30
4秒前
星辰大海的应助被15采纳,获得30
5秒前
搜集达人的应助被大气的嚓茶采纳,获得10
5秒前
体贴鹰发布了新的文献求助10
5秒前
仙八完成签到 ,获得积分10
5秒前
田様的应助被钟梓袄采纳,获得10
6秒前
CipherSage的应助被钟梓袄采纳,获得10
6秒前
hitech的应助被小橘子采纳,获得20
6秒前
爆米花的应助被钟梓袄采纳,获得10
6秒前
Crssss的应助被单纯乘风采纳,获得10
6秒前
6秒前
pp发布了新的文献求助10
7秒前
美羊羊羊完成签到,获得积分10
7秒前
7秒前
8秒前
8秒前
9秒前
冬瓜鑫发布了新的文献求助10
9秒前
9秒前
知白守黑完成签到,获得积分10
10秒前
斯文败类的应助被codwest采纳,获得10
10秒前
柒柒完成签到 ,获得积分10
10秒前
10秒前
10秒前
11秒前
哈47发布了新的文献求助10
11秒前
彩虹桥发布了新的文献求助10
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183091
求助须知:如何正确求助?哪些是违规求助? 9572406
关于积分的说明 21825003
捐赠科研通 7779812
什么是DOI,文献DOI怎么找? 3433837
关于科研通互助平台的介绍 2558045
邀请新用户注册赠送积分活动 2480046